Canonical: https://botbento.com/blog/anthropic-tool-choice-force-or-auto/ Format: Markdown representation of the public HTML page. [Home](/) / [Blog](/blog/) FIELD NOTES / 5 MIN READ # Should Your Bot Force a Tool Call, or Let Claude Decide? Claude's tool\_choice field lets you move from 'the model may call a tool' to 'the model must call this tool,' but a few current models reject forced calls outright and parallel tool use adds a second, independent switch. This piece works through when to force a call, when to leave it on auto, and what breaks if you guess wrong. By BotBento Editorial · Published 2026-10-13 · Updated 2026-10-13 AI-assisted editorial: researched and drafted with AI using the primary sources linked below. Examples are illustrative; they are not measured product results. [Editorial policy](/editorial/). ## In this article - [The Four tool\_choice Modes](#four-modes) - [Not Every Model Accepts a Forced Call](#model-restrictions) - [Forcing a Tool Is Not the Same as Forcing One Call](#parallel-calls) - [Worked Example: A Calendar-Booking Bot](#worked-example) - [A Checklist Before You Force a Call](#decision-checklist)[Read as Markdown ](/text/blog/anthropic-tool-choice-force-or-auto/index.md) ## Key takeaways - tool\_choice has four modes (auto, any, tool, none); forcing a call with any or tool skips the model's own text reasoning and jumps straight to a tool\_use block. - Claude Opus 5.5, Sonnet 5.5, Fable 5.1 and Mythos 5.1 reject forced tool\_choice with a 400 error. On those models, auto can still skip the call; strict tool use only validates inputs if a call occurs. - disable\_parallel\_tool\_use limits a response to one tool call; it does not prevent duplicate side effects across retries. Use an idempotency key and verify the tool result for writes or sends. ## The Four tool\_choice Modes Claude's Messages API accepts a tool\_choice field on every request. The default, auto, lets Claude decide on its own whether a turn needs a tool call at all. The alternative is to force one: setting tool\_choice to a specific tool name, or to any available tool, tells Claude it must produce a tool\_use block instead of a plain text answer, even if Claude would otherwise have just answered in words. Forcing a call changes more than which tool runs. When tool\_choice is any or tool, Claude's response starts directly with the tool\_use block, so there is no preceding explanation or reasoning text attached to that turn the way there is under auto. If you want Claude to narrate its choice while still nudging it toward a specific tool, the documented alternative is to keep tool\_choice on auto and put an explicit instruction naming the tool in the prompt instead. Sources: [Define tools - Claude Platform Docs](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools). ## Not Every Model Accepts a Forced Call Forcing a tool call is not universally supported. Claude's own documentation lists Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1 and Claude Mythos 5.1 as models where tool\_choice set to any or tool returns a 400 error, while auto and none keep working normally on those same models. The documented substitute is auto combined with strict tool use, which guarantees schema-valid inputs without forcing the call itself, or structured outputs when you need the response in a fixed JSON shape. Extended thinking adds a second restriction that is independent of which model you're on. Manual extended thinking blocks any and tool outright and only accepts auto or none. Adaptive thinking, the kind that's on by default for some models, is different: it doesn't block a forced call, but a forced call does skip the thinking step, so the response starts with the tool call and carries no thinking block for that turn. If your bot picks its model dynamically, or you're testing against a newer Claude release, check this restriction before you ship a flow that forces a call. A hard 400 on a turn your bot assumed would succeed is a bad place to discover the restriction for the first time. Sources: [Define tools - Claude Platform Docs](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools). ## Forcing a Tool Is Not the Same as Forcing One Call tool\_choice controls whether and which tool Claude requests. The disable\_parallel\_tool\_use flag, set inside tool\_choice, limits how many tool calls Claude may request in a single response. By default, Claude may call multiple tools in one response, which is useful for independent lookups but risky when calls have side effects or depend on an order. The two settings combine predictably: with tool\_choice set to auto, turning on disable\_parallel\_tool\_use means Claude requests at most one tool in that response, but may still answer in plain text instead. With tool\_choice set to any or tool, the same flag makes Claude request exactly one tool in that response. For a bot that writes to a calendar, a database, or sends a message, the application must still execute the call, verify its result, and deduplicate retries; this flag alone does not guarantee exactly-once effects. Anthropic's own computer-use and browser-use tools have a stricter built-in rule for this problem: when Claude returns several calls to tools in the same toolset in one turn, the documentation says to run them sequentially in the order they appear and stop at the first failure, with each tool defining what to return for the calls you skip. That's a useful pattern to borrow even for your own custom tools if a batch of calls has to stay ordered and failure-stoppable. Sources: [Define tools - Claude Platform Docs](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools), [Parallel tool use - Claude Platform Docs](https://platform.claude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use). ## Worked Example: A Calendar-Booking Bot Illustrative example. Say a bot has three tools: check\_availability, create\_event, and send\_confirmation. For most of the conversation, tool\_choice stays on auto. The bot might check availability, discuss options with the user in plain text, revise the time, and check again. Forcing a tool call here would strip out the back-and-forth text that makes the conversation usable. The moment changes at the confirmation step. Once the user says 'book it,' the bot should not be allowed to just reply with a friendly text message and silently skip the booking. This is the turn to set tool\_choice to the tool mode, naming create\_event directly, with disable\_parallel\_tool\_use on so the model can't also fire off a second, unrelated tool call in the same turn. On models that support forced use, that combination makes one create\_event request mandatory in the response. The application must execute it, confirm success, and use a booking idempotency key so a timeout or retry cannot create a second event. Before shipping that confirmation step, check which model is serving the request. If it's one of the models that rejects forced calls, the fallback is to keep tool\_choice on auto, add an explicit system or user instruction naming create\_event, and turn on strict tool use so any tool arguments that do come back are schema-valid. This fallback does not guarantee a call: auto may still produce text only. Treat that as no booking, and never show a confirmation until create\_event succeeds and its event ID is recorded. Sources: [Define tools - Claude Platform Docs](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools). ## A Checklist Before You Force a Call Forcing a tool call is a narrow tool for a narrow problem: a step where the model must request a specific function in its next response. Execution, success, and retry safety remain application responsibilities. Reach for it sparingly, and verify model support before you depend on it in production. - Default to auto for anything conversational, exploratory, or where the model answering in plain text is a valid outcome. - Force tool\_choice only at a commitment point: a write, a send, a charge, a booking. - Check the model's forced-tool-use support before relying on it; some current Claude models return a 400 on any or tool. - If the model rejects forced calls, fall back to auto plus an explicit instruction naming the tool, plus strict tool use for schema validity. - Pair a forced call with disable\_parallel\_tool\_use to limit the response to one call, then use idempotency and outcome checks for the side effect. - Don't force a call under manual extended thinking; it's not supported regardless of model. ## Primary sources Sources checked 2026-10-13. Standards and product documentation can change; follow the linked version when implementing. - [Define tools - Claude Platform Docs](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools) — Anthropic - [Parallel tool use - Claude Platform Docs](https://platform.claude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use) — Anthropic BotBento is in development. [Suggest a correction](/contact/).