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

Adds substantial behavioral context beyond the annotations: it discloses that the call returns a queued operation immediately, that this is not provider-completion confirmation, the required polling step, and the retry rule for the operationId. These are real operational traits not covered by readOnlyHint/idempotentHint/destructiveHint.

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?

Three tight sentences, front-loaded with purpose then async contract, with no filler. Each sentence carries actionable information. Minor miscue: 'uncertain send' is odd wording for a star operation, but it does not waste space.

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 async-return burden well by explaining the queued operation and pointing to get_mail_action with the returned operationId. It omits any guidance on the required accountId/messageId, so it is not fully complete for a 4-parameter tool.

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 only 25% – only operationId is documented in the schema. The description adds practical meaning for operationId (retry semantics) and implicitly covers isStarred via 'email is starred', but leaves accountId and messageId unexplained. Partial compensation for a low-coverage schema.

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 precise verb and resource ('Set whether an email is starred'), which is clearly distinct from siblings like mark_email_read or archive_email. It does not explicitly name a sibling, but the purpose is unambiguous without needing to open a schema.

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?

The description describes the post-invocation workflow (poll get_mail_action, don't retry with a new operationId) but never states when to choose this tool over an alternative or any preconditions. Usage is implied by the async workflow rather than explicitly framed.

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