audio.measure

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

With no annotations, the description carries the full behavioral burden; it does disclose that this is a loudnorm-based measurement and names the three metrics, which implies a read-only analysis. However, it does not say the call is non-destructive, whether it decodes the whole file (cost/latency), or how results are returned.

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?

One sentence, front-loaded with the verb and the returned metrics, no filler. Every clause (metrics, media file, ffmpeg loudnorm) contributes information.

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 read tool with no annotations and no output schema, the description names the three returned values with units, which is most of what an agent needs. The remaining gap is the shape of the response (structured fields vs raw ffmpeg output), which is never stated.

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?

There is a single parameter with 100% schema description coverage ('Path to a local audio or video file'), so the schema already does the work and the baseline is 3. The description adds nothing about the input beyond what the schema states.

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?

Specific verb (measure) plus the exact resource set (LUFS, dBTP, LRA) and the underlying mechanism (ffmpeg loudnorm), so an agent knows precisely what it gets back. It does not explicitly contrast itself with the sibling audio.loudnorm, so differentiation is left to inference from the verb 'measure' vs 'normalize'.

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 only implied: an agent can infer 'use this when you need loudness numbers rather than to fix them,' but the description never states when to call this versus audio.loudnorm, probe, or transcribe. No preconditions or exclusions are given.

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