analyze_audio

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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds the constraint that it operates on a single bounced render and clarifies the read-only nature in prose ('Read-only'), which reinforces rather than merely repeats the annotation. The behavioral burden is largely on annotations here, and the description adds value by scoping input to a rendered WAV rather than arbitrary audio.

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 short sentences, front-loaded with the core purpose and metrics, followed by a usage directive. Zero filler or wasted words. The sibling differentiation is compactly embedded in the same lines.

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 single-input read-only analysis tool, the description is complete: it lists what metrics are returned, scopes input to a single render, and names the folder-level alternative. An output schema exists, so return-value details are covered structurally. The only minor gap is not describing the shape of the spectral band energy output, but the output schema presumably covers that. Given low complexity and full annotation coverage, this approaches completeness.

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 description coverage is 100% — the single 'path' parameter is already well documented as a rendered WAV file with path resolution. The description reinforces that it should be a 'bounced render' (adding slight semantic nuance beyond the schema's 'rendered WAV file'), but beyond that it adds minimal parameter-level detail. Baseline 3 is appropriate given full schema coverage.

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?

The description states a specific verb+resource ('Analyze a rendered WAV file into mix metrics') and enumerates the metrics produced (loudness LUFS/LRA, RMS, peak, spectral band energy, stereo width). Clearly distinguishes from the sibling analyze_render_dir, which is a folder-level version. This is exemplary purpose clarity.

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?

Explicitly states 'Use on a single bounced render' and explicitly names the alternative: 'For a whole folder of renders, use analyze_render_dir instead.' This is exactly the when/when-not/alternatives guidance the rubric rewards.

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