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

Annotations only say non-readonly and non-destructive; the description adds the substantive behavior: the old secret remains valid for 15 minutes, so no immediate 401, and identity/grants/tree are untouched. It does not state required permissions or whether the old secret can be force-revoked early.

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?

Three short sentences, front-loaded with the operation and its invariants, then the grace-period behavior, then the targeting rule. Nothing is repeated from the annotations and no sentence is filler.

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 need no explanation, and the single parameter is covered by the description. The remaining gap is operational (auth requirements, whether rotation is idempotent or rate-limited), which is minor for a one-parameter tool.

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 0% — the parameter has no description and only a bare default of "self". The description compensates well by explaining that "self" means your own token and any other value means a descendant token, which is meaning the schema does not supply.

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 (rotate) plus exactly what is rotated (the secret, not the token) and enumerates what stays unchanged (id, agent_id, grants, tree). This implicitly separates it from renew_token and revoke_token, though it never names those siblings.

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?

"Rotate yourself (\"self\") or a descendant" gives clear targeting scope, and the 15-minute overlap window implies the intended use case (switching a live session without a 401). It stops short of saying when to prefer this over renew_token or revoke_token, so the agent must infer.

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