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

Annotations only say this is a non-read-only, non-idempotent, open-world mutation. The description goes well beyond them by disclosing that the call is queued and asynchronous, that the immediate return is NOT proof of provider completion, and the exact retry discipline to follow. That is the kind of context annotations cannot carry.

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 caveat and retry rule, with no filler. Minor blemish: 'an uncertain send' borrows send-oriented phrasing for a star operation, which slightly muddies an otherwise tight passage.

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 correctly explains what comes back (a queued operation plus operationId) and how to resolve it. What is missing for a mutation tool is failure handling and any account/permission expectations, but the async contract itself is fully covered.

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 50%: messageId and operationId are well documented in the schema itself, while accountId and isStarred have no description. The description adds no parameter-level meaning, though the two undocumented params are near-self-explanatory (account string, boolean flag), so the baseline 3 holds rather than dropping lower.

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 first sentence states a specific verb and resource ('Set whether an email is starred'), so an agent knows exactly what state is mutated. It does not explicitly say how it differs from the similarly-shaped mark_email_read sibling, which keeps it short of 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?

It gives concrete operational guidance: use get_mail_action to poll with the returned operationId, and reuse the operationId rather than minting a new one on retry. That is clear when-and-how guidance, though it never states when not to use this tool or names an alternative for the flag-setting case.

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