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

Annotations only declare the safety profile (readOnlyHint=false, idempotentHint=false, openWorldHint=true); the description adds substantial context beyond them by disclosing the asynchronous queued-operation model, that the return is not confirmation of provider completion, and the polling requirement. The phrase 'Never retry an uncertain send' is odd wording for a read-state tool (copy-paste from a send tool), but it does not contradict the annotations.

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?

Four short sentences, front-loaded with the core action before the async caveats. Slight redundancy in the retry instruction, which largely restates the operationId schema description, but there is little waste overall.

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 an async mutation with no output schema and 4 parameters, the description covers the operation lifecycle and polling path well, which is the most important missing piece. It still omits the semantics of the non-operationId parameters and gives no sense of what the queued operation ultimately affects, leaving the definition only partially complete.

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 only 25% – just operationId is documented, and its idempotency semantics are already in the schema. The description references operationId for polling but never explains accountId, messageId, or the polarity of isRead (true = read vs unread), so it fails to compensate for the coverage gap.

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: 'Set the read state of a message.' An agent can immediately tell this mutates read/unread state, distinguishing it from setters of other attributes like set_email_starred or move_email. It does not, however, explicitly name a sibling it replaces or defers to, which keeps it below a 5.

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 post-invocation guidance (poll get_mail_action with the operationId, don't retry with a new operationId) and names the correct follow-up tool, but never states when to choose this tool over alternatives or any precondition for the read-state change itself. Usage context is implied rather than stated.

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