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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), so the bar is lower, and the description still adds real behavior: the call is project-scoped to the explicit project_id and returns the project identity alongside results. It does not mention pagination or result size, but for a read-only library listing that is minor.

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 two operative constraints (PROJECT-SCOPED, READ) before the editorial content, and the sentences are dense rather than padded. The trailing placement policy is arguably add_sfx territory and lengthens the entry more than a pure listing tool needs.

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 no output schema, the description carries the return-shape burden and largely does: it conveys that entries carry usage guidance and hit levels plus the echoed project identity. Enough for an agent to call it and use the result correctly, though it never says how many sounds come back or in what order.

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, giving a baseline of 3. The description adds some role-filter color by enumerating the sound categories (whoosh, swish, impact, risers, shutter, keyboard, click, pop, tick, ding, glitch, cash register, heartbeat) that map to the optional role filter, which is a modest lift beyond the schema's short 'e.g. whoosh, click, riser'.

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?

States a specific verb ('READ: Valmera's sound library'), the resource, and the payload an agent can expect — categories like whooshes, risers, shutters with 'when to use each and its measured hit level'. It is clearly distinguishable from the sibling list_music_library and from the add_sfx/remove_sfx/move_sfx mutation tools.

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?

It explicitly routes the agent to the follow-up call (add_sfx(storage_key='sound:<id>', at=<frame>, gain_db unset)) and gives placement policy (zero by default in a podcast short, at most 1-2, never on captions or spoken-word puns). What's missing is an explicit statement of when to reach for this tool over list_music_library or add_library_music, so selection between siblings is left partly to inference.

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