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

Annotations already establish readOnlyHint=true and non-destructive, closed-world behavior. The description adds genuinely new context: return values are normalized 0-1 peak/RMS samples. It does not disclose sampling resolution, the points cap, or what happens when points is omitted.

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 sentence that front-loads the resource and return format before the use case. 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?

For a read-only, no-output-schema tool the description does convey the shape of the return data, which is the key gap filler. However, the undocumented 'points' parameter and the lack of any mention of output structure or resolution leave real holes for an agent tuning sampling density.

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 67%; 'media' and 'project' are documented, but the integer 'points' parameter has no description in the schema and the description only hints at it via 'sampled.' The 1-2000 range and default behavior are left unexplained.

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?

Names a specific resource (peak and RMS audio levels) plus the normalized range 0-1, so an agent knows exactly what comes back. It does not differentiate itself from siblings like measure_loudness, detect_silence, or waveform_image, which cover adjacent ground.

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 clause 'for finding silence, beats or the loudest moment' gives intended use cases, which is more than nothing. But it never says when to prefer this over detect_silence or measure_loudness, nor any exclusions or prerequisites.

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