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

Beyond the readOnlyHint annotation, it discloses important behavior: results are 'never a secret', returned fields are enumerated, status values are spelled out, and it explains that types your scopes cannot read appear under `omitted`, plus the auth/scope requirements. This is exactly the kind of auth-and-partial-result context annotations do not convey.

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?

Front-loaded with the core purpose and the 'never a secret' reassurance, then field list, then parameter/enum details, then permissions. The single long field enumeration is dense but each item conveys what the caller receives; no filler sentences.

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 compensates by enumerating the returned fields (type, name, status, last-4, scopes, repo, expiry, last use with IP/client, use count, rotation state) and explains permission requirements and the omitted-types behavior. An agent has everything needed to call and interpret it.

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 description coverage is 100%, so the `type` parameter is already fully documented, and the description largely restates the same enum values and prefixes. It adds only the marginal note that omitting `type` returns all three and that unreadable types surface under `omitted`, so the baseline 3 is appropriate.

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 and resource ('List your own tokens') with explicit scope and immediately clarifies it never returns secrets. The scope word 'own' and the enumerated token types distinguish it from single-token and repo-scoped siblings like get_token and list_repo_tokens.

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?

Provides clear applicability context: it lists the caller's own tokens, tells you the token types available via `type`, and states the scopes needed to read each type ('user' scope for PATs, 'repo' for others). It does not, however, explicitly name a sibling to use instead when you want repo-scoped or single-token reads.

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