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

Annotations already mark this as non-read-only but non-destructive and open-world; the description adds the important behavioral fact that no email is sent, confirming the side-effect boundary. It stops short of disclosing auth requirements, whether an existing draft is overwritten, or what identifier comes back.

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?

Two tight sentences, front-loaded with the action and followed by the key constraint. No filler or repetition.

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 a write tool with 5 parameters at 40% coverage and no output schema, the description is too thin: it never explains the role of emailAddress/emailAccountId nor what the caller gets back (e.g., a draft ID). An agent could invoke it but lacks the context to shape the request 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 only 40% schema description coverage, the description should compensate, but it merely restates the three required fields (to, subject, body) already covered by the schema and says nothing about emailAddress or emailAccountId. The ambiguous overlap between 'to' and 'emailAddress' is left completely unexplained.

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 clear verb+resource ('Create a mailbox draft') and names the three fields it takes, so the core action is unambiguous. However, it does not differentiate itself from the sibling save_mail_draft, which an agent could easily confuse with this tool.

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?

'Saves the draft for review without sending email' implies the use case (compose-but-don't-send) but never states when to prefer this over send_mail or save_mail_draft. Usage is inferable rather than explicit, and no exclusions or prerequisites are given.

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