Tag audio

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

Adds substantial behaviour beyond the annotations: nothing is uploaded when reusing an analysis_id, no extra run is consumed, a file_path path silently triggers segment first, and the call blocks for 'a few minutes' while stems are produced after a fresh analysis. It also says where outputs land (`metadata` with genre/song_tags/description, plus the results folder). It does not discuss repeat calls or failure modes, so it falls short of 5.

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 with the purpose, then input choice, then the latency caveat and output location — a sensible order with no filler. The second sentence ('Give the analysis_id from segment: nothing is uploaded...') is slightly compressed and harder to parse than the rest.

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?

Annotations and a full output schema already cover the safety profile and return shape, so the description only needs to explain inputs, run accounting and latency — all of which it does, including where tags are saved. Minor gaps, such as behaviour on re-tagging an already-tagged track, remain.

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%, so both parameters are already documented, and the description's statements about analysis_id reuse and file_path triggering segment largely restate the schema. Its added value is workflow framing ('Give the analysis_id from segment') rather than new meaning, so the baseline 3 applies.

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 and resource plus an enumeration of the outputs produced (genre, moods, instruments, artist tags for mix and each part, plus a written description), which lets an agent tell it apart from analyze, audio_features and get_lyrics. It stops short of naming a sibling it supersedes, keeping it at 4 rather than 5.

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?

Gives clear routing guidance in both directions: 'Give the analysis_id from segment' to reuse an existing analysis, and 'A file_path runs segment first (one run)' for an unanalysed track. What is missing is explicit contrast with alternative extraction tools such as audio_features or analyze, so the agent must infer that split.

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