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

With no annotations, the description carries the full burden and does so: it discloses that recognition runs on this server (privacy), the exact cost (2 credits per minute), the async job_id polling pattern via get_job, and the 1-hour result-link expiry. These are precisely the behavioral traits an agent cannot infer from the schema.

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?

Four short sentences, each earning its place: capability and output first, then privacy, then cost/async mechanics, then result lifetime. The most decision-relevant facts are front-loaded with zero filler.

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?

There is no output schema, so the description usefully summarizes the return value (transcript plus ready-made .srt and .vtt files). Combined with cost, async behavior and expiry, an agent has everything needed to call this correctly in one shot.

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%, so url, language and translate_to_english are already documented with formats and defaults. The description adds only the notion of timestamps in the output and does not extend meaning for any individual parameter, so the 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?

States a specific verb and resource ('turn the speech in a video or audio file into text') and names the granularity (timestamps). It is clearly distinguishable from siblings like extract_audio, add_captions and subtitle_convert because it produces the transcript itself rather than manipulating existing subtitles.

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?

Gives the operational context an agent needs: long jobs return a job_id to poll with get_job, and result links expire in 1 hour. It does not explicitly say when to prefer this over sibling tools such as add_captions or analyze_media, so it stops short of full alternative routing.

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