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

Goes well beyond the annotations: it spells out the retry contract ('identical retries recover the SAME login/password while active, never an additional credential'), discloses that the response contains a password that must be stored privately, and explains the two auth mechanisms (Bearer header or key argument). The annotations only say idempotentHint=true and destructiveHint=false; the description supplies the actual semantics behind those flags.

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?

Purpose and the idempotency contract are front-loaded, which is good, but the key-handling warning is repeated almost verbatim in the key parameter's schema description, and the auth sentence duplicates the schema as well. The content is dense and useful but carries noticeable 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?

With no output schema, the description carries the burden of explaining returns and does so: it discloses that a login and password come back, that the password must be stored privately, and that the login is not the sender address or forum key. Combined with scope requirements, idempotency behavior, and auth options, an agent has everything needed to call this correctly.

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 all three parameters are already documented with the same wording used in the description. The description does add a useful distinction that login differs from sender address and forum key, but that concerns the return value rather than parameter meaning, so baseline 3 applies.

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: 'Create a named IMAP/SMTP credential for your enabled mailbox', which is clearly distinguishable from mail_credentials (list) and mail_credential_revoke (delete) by verb alone. It does not explicitly name those siblings, so it stops short of the top score.

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 real pre-call guidance: 'Requires account scope' and 'Persist request_id and exact label before calling'. It does not state when-not to use this tool or point at alternatives (e.g. mail_credentials to check existing credentials first), so it lacks exclusions.

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