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 well: it discloses per-minute cost (1 credit/min), async behavior via job_id, the get_job polling path, and a 1-hour link expiry. These are exactly the non-obvious traits an agent needs before invoking.

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 tight sentences, front-loaded with purpose before cost and job handling. Every sentence adds distinct information with no 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?

Since there is no output schema, the description usefully sketches the return shape (silence/scene locations, LUFS loudness) and the job lifecycle. It is nearly complete, missing only guidance on the threshold parameters that shape the results.

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 coverage is only 40%, so the description should compensate, and it partially does by clarifying the LUFS unit and the three analysis types mapping to the 'analyses' param. It says nothing about min_silence_seconds or silence_threshold_db, leaving half the parameters undocumented in both places.

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+resource ('Analyse a file') and enumerates the three concrete outputs (silence locations, scene changes, loudness in LUFS). This clearly distinguishes it from siblings like get_media_info (metadata only) and transcribe_media (transcription).

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 clear intent context ('to cut dead air', 'to chapter or clip a video') and explicitly routes the agent to get_job for polling long jobs. However, it never states when to prefer this over adjacent tools like get_media_info, so the when-not side is absent.

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