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

Annotations only indicate non-readonly, non-idempotent, non-destructive, open-world. The description adds meaningful behavior: submission may wait up to 240 seconds and, if incomplete, returns a job_id plus a follow-up query action. This async/timeout behavior is not visible in the annotations.

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?

A single compact sentence front-loads the core action and then adds the two key behavioral facts (240s wait, job_id/next step). No filler or repetition.

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?

For a one-parameter async submission tool with an output schema and sibling get-job tool, the description covers the important operational details: input type, wait limit, and fallback job_id. It is slightly non-specific about the exact next query action/tool name, but the sibling list makes this recoverable.

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 description coverage is 100%, and the zvideo_id parameter is already well documented with source, numeric-string constraint, and exclusions. The tool description adds no parameter details beyond the schema, so baseline 3 applies.

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?

The description states a specific action (submit speech-to-text task) and resource (Zhihu standalone video identified by zvideo_id), plus the async wait behavior. It is clear, but it does not explicitly differentiate from the sibling zhihu_submit_video_speech_text_by_video_url by naming the alternative or stating 'use this when you have a zvideo_id, not a URL'.

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?

The context is implied rather than stated: it is for submitting via zvideo_id, and '未完成时返回 job_id 和下一步查询动作' hints at polling with the get-job sibling. The schema's parameter description warns not to pass video links/answer/article/question IDs, but the main description does not explicitly say when to prefer this tool over the by_video_url sibling or how to proceed beyond a vague 'next query action'.

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