Approve an access request

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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description adds real nuance beyond them: exact retries replay while different or stale decisions conflict, other app grants are preserved, a revoked person is never revived, and no invitations or remote tailnet calls occur. This materially extends the structured hints rather than restating them.

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?

Information-dense and front-loaded with the actor and the single-action guarantee before edge-case rules. Every sentence carries behavioral payload, though the density borders on over-packing.

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?

An output schema exists, so return values need not be explained, and the description adequately covers role gating, idempotency, conflict behavior, and grant preservation. The main gap is the unexplained `id` and `ack_never` parameters.

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 coverage is only 33%: the `for` lifetime param is fully documented in-schema, but `id` and `ack_never` are undocumented in both places. The description confirms duration selection and lifetime policy but does not explain `id` or the role of `ack_never`, so it only partially compensates for the coverage gap.

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 (approve) and resource (one in-scope access request) with the exact action scope: selecting duration within the scope maximum and binding expiry in one call. It is clearly distinguishable from siblings requests_deny and requests_list without opening any schema.

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?

Specifies the required actor (current portal owner in owner or people-manager role) and the condition splitting the two roles: only owner can create an unknown person, people-manager needs an existing person. It gives clear context but never explicitly routes to the alternative tool (requests_deny) for the reject case.

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