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

Annotations already cover the safe-read profile (readOnly, idempotent, non-destructive), so the bar is lower. The description still adds real value beyond them: the async behavior ('a long file takes a while the first time: it may answer with a job id (poll get_job)') and the cost signal ('Free'), plus output semantics (dBFS scale, −100 = silence). It does not describe pagination or the exact result shape, keeping it out of the top band.

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?

Front-loaded with the resource ('Loudness over time of a library video or sound file') before mechanism, units, use case and the async caveat. Dense but nearly every clause earns its place; the long first sentence is packed but not redundant.

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 carries the return burden and does so: RMS in dBFS per step, quiet segments (pauses/dead air), loud moments, all in seconds, plus a note that long files may return a job id to poll. That covers the practical calling contract, though result length/default step count is only partially addressed.

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 60%; the schema documents step, media and project but leaves to/from bare. The description compensates by clarifying the time axis ('all in seconds of the file') and the meaning of step readings (RMS in dBFS per step), effectively giving units to the undocumented from/to window parameters. It stops short of stating defaults or bounds for from/to.

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 resource (loudness/levels over time of a media file) and pins down the output units precisely: RMS in dBFS per step, with −100 = silence, the quiet stretches and the loudest moments in seconds. It also distinguishes itself from sibling transcript tools by noting it 'Finds where the talking is without transcribing.' An agent can tell this apart from get_media_transcript or view_media_frame without opening a schema.

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?

Usage is implied rather than stated: 'Finds where the talking is without transcribing' hints it is an alternative to transcript tools for locating speech, and 'Free' signals cost. But there is no explicit when-to-use/when-not or named alternative, leaving the agent to infer selection between this and the transcript/frame siblings.

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