credential_refresh

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

No annotations are supplied, so the description carries the full burden. It does disclose one genuinely valuable behavioral trait: kugou returns supported=false and that is not a failure, which stops an agent from retrying or reporting an error. It omits what happens when refresh is not possible (auth expiry, invalid cookie), whether it invalidates other sessions, and any rate limits.

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 short sentences, front-loaded with the action, then the edge case. The parenthetical platform list is partly redundant once the kugou sentence is read, but nothing else is wasted.

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 an output schema present, return values needn't be explained, and a single optional enum parameter is simple. Still, a mutation-adjacent credential tool with no annotations would benefit from stating prerequisites (valid existing credential) and what a failure looks like, which is 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 effectively 0% for the service parameter, so the description must compensate, and it does: it explains that the kugou enum value present in the schema is a no-op returning supported=false, resolving the exact ambiguity the schema creates. It does not mention the qq_music default or any format expectations, which keeps it short of a 5.

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?

"Force-refresh a shared credential" gives a specific verb and resource, and the platform list scopes it. It is clearly distinct from the credential lifecycle siblings (status, set_cookie, logout), though it doesn't name any of them for contrast.

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?

Usage is only implied by the word "force" – the agent can infer this is for renewing an expired session, but nothing states when to prefer credential_status or credential_set_cookie instead, nor any prerequisite such as needing an existing session. The one explicit caveat is the kugou no-op, which does function as a usage warning.

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