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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds substantial context beyond them: revoked entries are included, passwords are never returned, pages cap at 100, an account scope is required, and the key may persist in client task history. That last point is a real operational risk disclosure an agent would not otherwise know.

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?

Sentences are front-loaded and ordered sensibly: purpose, pagination, scope, then auth. The security warning about key retention substantially duplicates the wording already present in the key parameter's schema description, which is the main source of redundancy.

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 two-parameter, read-only listing tool with no output schema, the description covers scope, pagination, and what is excluded from results, which is enough to call it correctly. It stops short of indicating what metadata fields are actually returned, leaving the agent to infer the response shape.

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 both parameters are already documented, and the description's key/Bearer note largely restates the schema text. The one genuine addition is the cursor flow ('Up to 100 per page; follow next_cursor'), which explains iteration rather than just the field's meaning.

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?

The description gives a specific verb and resource ('List ... mail credential metadata') and immediately bounds the scope ('only your', 'including revoked entries; passwords are never listed'). Read versus write is unambiguous against siblings like mail_credential_create and mail_credential_revoke.

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 implied rather than stated: 'List only your mail credential metadata' plus the account-scope requirement tells the agent when this applies, and 'follow next_cursor' gives the pagination procedure. There is no explicit when-not or named-alternative guidance for choosing among the mail_* siblings.

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