Audio (read)

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

Annotations already declare readOnly/idempotent/non-destructive, so the description's main added value is operational: analyze_loudness and detect_silence are flagged as running via ffmpeg 'no Resolve needed', while other actions implicitly require a Resolve session. That is real context beyond structured fields; what's missing is any note on error behavior or cost for the ffmpeg actions.

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 purpose sentence followed by a tight, scannable action list where every bullet earns its place. The only redundancy is 'no side effects', which restates readOnlyHint, and the initial phrase is slightly compressed ('audio state').

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?

Given an output schema exists and return values need not be explained, this description covers the action surface, per-action params, required markers, and environment requirements. An agent could select and invoke any of the seven actions from this text alone.

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?

The schema only enumerates action names and defers params to 'additionalProperties'; the description fills that hole by listing each action's parameter names and marking required ones (item*, analyze_loudness(path, clip)). This is exactly the value the shallow schema cannot carry.

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?

Opens with a specific verb+resource ('Read audio state') and immediately enumerates all seven concrete actions with their inputs, so an agent knows exactly what the tool covers. The sibling contrast with audio_write is clear from the read/write naming plus 'no side effects'.

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?

'use it to find ids and check results' gives a concrete use context, and per-action notes mark which ones work without Resolve. It never explicitly routes mutations to audio_write or other siblings, so the when-not guidance is only implied by the read-only framing.

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