Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses that no new payment is needed and that it returns a call_id for polling. Annotations only provide openWorldHint, so description adds behavioral context. Could be improved by mentioning that answers are optional and the tool will proceed as-is if omitted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three well-structured sentences, each conveying essential information: action and context, prerequisite, financial implication, and return value. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, description specifies the return value (call_id for polling). It covers prerequisite, usage, financial impact, and next steps. Additional context like error handling would elevate but is not necessary for typical usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions cover both parameters. Description adds value by explaining that 'answers' keys are question strings and values are answers, and that omitting them confirms as-is. This clarifies usage beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the action ('Confirm an AI call') and the context ('after reviewing push-back questions, optionally providing answers to missing info'). Distinguishes from sibling tool ai_call by specifying the prerequisite state 'pending_confirm'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use: 'Required when ai_call returns state="pending_confirm"'. Also notes financial aspect ('Uses the original payment — no new payment needed') and subsequent polling step ('Returns call_id for polling with check_job_status(jobType="ai-call")').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.