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

Annotations already declare read-only/non-destructive, but the description adds real value: the specific signals checked (domain validity, last-touch within three days, send volume vs mailbox age) and the meaning of HOLD vs REVIEW outcomes. It also reinforces "it sends nothing," consistent with 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?

Front-loaded with the purpose, then the enumerated checks, then result semantics and a read-only note. The check list is dense but each item earns its place; slightly long but well-ordered.

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 an output schema present, the description needn't explain return values, and it covers purpose, checks, and result codes. The only shortfall is thin parameter guidance, but overall it equips an agent to call it 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?

At 40% schema coverage the description should compensate, but it never maps inputs to meaning: the required companyId (UUID wrapper) is unmentioned, and to/subject/body/relationshipId are only obliquely implied by "one draft" and "same relationship." This leaves notable gaps for a 5-param tool.

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 (checks) and resource (one draft before save/send) and enumerates exactly what is validated, so the function is unambiguous. It does not name any sibling (e.g., record_touch, get_send_windows) to differentiate against, keeping 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?

"before it is saved to the mailbox or sent" gives a clear trigger point for use, and the HOLD/REVIEW semantics tell the agent what to do with the result. No explicit alternatives or when-not conditions are named, so it stops short of 5.

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