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

Annotations declare readOnlyHint=true and openWorldHint=true, which the description complements by stating it does not create new tasks or trigger reprocessing, reinforcing the read-only nature. It adds a concrete behavioral trait: the 240-second maximum wait per call, which is not in the annotations. No contradictions detected.

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?

The description is a single, dense sentence that front-loads the core purpose (query an existing job) and includes essential behavior (240s wait, no side effects). Every word earns its place; no fluff or redundant elaboration.

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 tool with an output schema present, the description adequately covers when to use it, what it does, and its behavioral limits. The only minor gap is the lack of explicit guidance on how long to keep polling or when to stop (e.g., 'until completion'), but the presence of an output schema and the wait-time hint make this sufficient for an agent to infer appropriate 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 description coverage is 100%, with the job_id parameter fully documented including its source and exclusion of post_id. The description repeats the job_id origin ('用户提供的有效 job_id，或...submit 工具返回的 job_id') but adds no new parameter-level semantics beyond what the schema already states. Baseline 3 is appropriate given the schema carries the burden.

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 clearly identifies the tool as a query operation for an existing speech-to-text job ('继续查询' = continue querying), tied to a job_id from the submit tool. It distinguishes itself from the submit siblings by explicitly stating it does not create new tasks or trigger reprocessing. However, it does not explicitly state whether it returns status, progress, or final result, leaving some ambiguity for the agent about the exact output nature.

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 description implies usage after a submit call by referencing the submit tool's returned job_id and forbidding post_id. It also provides context on the wait behavior (up to 240 seconds) and side-effect-free nature, guiding the agent to use it for polling without re-submission. It does not explicitly say 'use this instead of the submit tools', but the contrast is implicit and sufficient.

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