audio_diff

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

With no annotations, the description carries full burden. It discloses the comparison is in feature space (not byte-for-byte), lists dimensions checked, and explains verdict types. No mention of side effects or performance, but sufficient for transparency.

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?

Two sentences: first defines purpose and output, second gives usage guidance and clarification. No redundant words, appropriately front-loaded.

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 no output schema, description explains verdict types and mentions JSON output option. Parameters are well-covered by schema. Could mention error handling or file size limits, but overall complete for the tool's complexity.

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 has 100% coverage with descriptions for all parameters. The tool description adds minimal extra semantic meaning beyond the schema; e.g., it mentions 'per-segment RMS' which relates to window_ms, indirectly. Baseline 3 is appropriate.

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 clearly states the tool compares two audio files in feature space (loudness, onsets, pitch, key, per-segment RMS) and reports a verdict. It distinguishes from siblings by focusing on comparison, while other siblings like probe_audio or spectrogram are for single-file analysis.

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 when to use: to check if re-render, edit, or platform change altered audio in a meaningful way. Also clarifies that a 'different' verdict is normal, not a failure. Does not list when not to use or alternatives, but context is clear.

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