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

Goes well beyond the destructiveHint=true annotation by specifying exactly what is destroyed: the previous secret and any other sessions. It also states the compensating guarantee that the current MCP session stays authenticated, which is the key thing an agent needs to know before triggering a destructive, non-idempotent operation.

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?

A single sentence with three front-loaded, non-redundant clauses: the action, the destructive scope, and the session-preservation caveat. Nothing is padded and no sentence restates structured fields.

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?

Annotations already declare the destructive/non-idempotent/closed-world profile and the schema is empty, so the description need only explain effects — which it does. The one remaining gap is how the new secret is delivered back (no output schema exists), though 'mint' strongly implies it is returned.

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?

The tool takes no parameters, so the schema carries no semantics to compensate for; the baseline is 4. The description is consistent with a zero-argument call and adds no misleading parameter expectations.

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?

Names a specific verb chain and resource: mint a fresh agent_secret, invalidate the old one, preserve the current session. No sibling tool touches credentials (sign_in, register_key, recover are adjacent but distinct), so an agent can identify this as the credential-rotation tool at a glance.

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 — the agent must infer that this is called when a secret needs rotating. There is no explicit trigger condition (e.g., compromise, scheduled rotation) and no statement of when not to call it, though with zero parameters and no alternative rotation tool there is limited ambiguity.

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