auth_poll

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

Annotations already declare this is not read-only, is open-world, and is not idempotent, so the mutation profile is partly covered. The description adds genuinely new context: the token is stored securely and deliberately withheld from the model, which explains why a successful poll produces no visible secret and reinforces why repeated calls are safe to sequence. It stops short of describing what happens on pending/denied states.

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, each carrying distinct information: one about the call semantics, one about the security behavior of the result. Nothing is repeated from annotations or the schema, and the operational guidance is front-loaded.

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 burden of explaining what a poll returns, and it only covers the token-storage side effect. It never states how pending, approved, or expired states are surfaced to the agent, which is the key thing a polling tool must communicate.

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?

With zero parameters and 100% schema coverage, there is nothing for the description to disambiguate; a baseline 4 applies. The description doesn't need to and does not restate any parameter details.

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 description names a concrete verb and resource ('Check browser approval') with the scope qualifier 'once', so an agent knows this is a single poll of a pending auth flow rather than a status read or an initiation. It does not explicitly distinguish itself from the sibling auth_status, so distinguishing which one to call is left partly to inference.

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?

'Check ... once, respecting server polling intervals' implies this should be called repeatedly on an interval while waiting for approval, which is useful but phrased as a constraint rather than guidance. There is no explicit statement of when to prefer this over auth_status, auth_begin, or auth_logout, so the agent must infer the sequence.

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