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

Annotations only say destructiveHint=true; the description specifies exactly what is destroyed and when — the old secret is killed immediately at grace_seconds=0, survives up to 604800 seconds otherwise, and an earlier grace period is cut short by a second rotation. It further discloses the one-time secret return, CAS concurrency guarantees, authorization scopes, and audit logging.

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?

Single dense paragraph, front-loaded with the core action and return value, then the optional parameters in descending importance. Nearly every clause carries behavior (grace window, CAS, type/scope), though the run-on density makes it slightly harder to scan than a bulleted layout would.

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?

For a destructive mutation with no output schema, it covers everything an agent needs: what is created, what is invalidated, the one-time nature of the returned secret, timing control, concurrency safety, and permission prerequisites. Nothing material is left for the agent to infer.

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 100%, so baseline is 3; the description earns more by explaining consequences rather than restating types — grace_seconds bounds and the '0 kills it now' effect, the compare-and-swap meaning of expected_rotation_count, and the type mapping to prefixes (glc_/gcft_/gcdt_) plus their scope requirements.

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?

Opens with a specific verb and resource ("Rotate one of your tokens") and immediately defines the semantics: mint a new secret with the same name, scopes/permissions, repository and expiry, returned ONCE as `token`. That distinguishes it clearly from siblings like merjax_create_repo_token, merjax_revoke_token and merjax_get_token.

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?

Gives concrete context: use `expected_rotation_count` from merjax_get_token's rotationCount for compare-and-swap, and states required scopes per token type ('admin' for PATs, 'repo' for repo/deploy). It does not explicitly contrast rotating with revoking or creating a fresh token, so the alternative-selection guidance is implied rather than spelled out.

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