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

Annotations already cover read-only, idempotent, non-destructive, and closed-world, so the bar is lower; the description still adds real value by disclosing return shapes ({total, offset, returned, scenes}, {tracks}) and the non-obvious fallback that an unmatched audio_library query returns the library's moods and genres. It also notes music timing is in seconds, a behavioral detail the annotations cannot express.

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 compact fragments, no filler, and each sentence maps to one action. The tradeoff is that it is not front-loaded with a purpose statement and reads as terse notes rather than prose.

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?

With nine parameters, no output schema, and rich 100% schema coverage, the description supplies exactly the missing piece: what each action returns and the shape of the scenes payload. Nothing an agent needs to invoke it correctly appears absent.

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 the baseline is 3; the description does explain the meaning of the scenes paging envelope and the seconds unit for music, but it largely paraphrases the action enum descriptions already in the schema. Interactions between mood, genre, search, and category are left to the schema.

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 title plus the per-action breakdown makes clear this is a read tool over the editor timeline, music tracks, and audio library, and it explicitly ties audio_library output to editor_edit. However, the description itself opens mid-thought with 'scenes:' rather than a lead sentence naming the resource, so an agent must assemble the purpose from three fragments.

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?

The only routing signal is 'audio_library: tracks to add with editor_edit', which implies this read feeds a specific sibling, plus a fallback note when nothing matches. There is no statement of when to choose scenes vs music vs audio_library, and no exclusions versus other read siblings such as storyboard_read or script_read; the action enum in the schema does most of the work.

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