Preferences

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

Annotations already declare destructiveHint=true and openWorldHint=true; the description adds real context on top by bounding what destruction is possible (two preference keys only) and by promising 'Original value and readback are returned', which enables rollback verification. It does not say whether the change persists across restarts or how errors surface, so it is not a 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?

Two dense sentences, front-loaded with the read behavior and the write restriction, with no filler or restatement of the tool name.

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 usefully discloses that the original value and readback are returned, and it bounds the mutation surface. The remaining gap is the concrete preference identifiers and accepted value formats, which the 0%-coverage schema does not supply either.

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 0%, so the description carries the burden; it does clarify that 'name' identifies a preference and that 'set' is limited to sample rate and channel count, and that 'value' is echoed back. However it never gives the actual preference key strings or valid value ranges for sample rate/channel count, leaving the enum-driven action only partly compensated.

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 specific verbs and a resource ('Get a preference or list available preferences'), then immediately narrows the write path to a whitelist. An agent can tell the read actions apart from the mutation action from the first sentence alone.

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 a clear exclusion list: set 'never changes modules, UI language, devices or pipe settings', which tells the agent when this tool will fail or is the wrong choice. It stops short of naming a sibling alternative for the excluded settings, so it lands at 4 rather than 5.

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