send-mail

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

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description adds meaningful behavioral context: the tool acts 'as the signed-in user,' performs compose+send in a single step, and requires confirm=true plus explicit user approval before executing. These are safety-relevant traits not present in the annotation block, though it stops short of disclosing irreversibility details.

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 sentences, each earning its place: the core action is front-loaded, the safety requirement is stated in the second sentence, and the routing to an alternative closes it. There is zero filler or repetition of schema content.

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 9-parameter write operation, the description covers purpose, safety gate, and alternative routing, while the schema covers parameters at 89%. Minor gaps remain: no mention of what the tool returns on success/failure and no explicit statement that a sent email cannot be unsent, though the strong confirm-gate emphasis partially mitigates this.

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 89%, well above the 80% threshold, so the schema carries the parameter documentation burden. The description's mention of 'confirm=true' reinforces the safety gate but does not add semantics beyond what the confirm parameter's own schema description already states, so baseline 3 applies.

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 description states a specific verb+resource: 'Compose and SEND an email in one step as the signed-in user.' It clearly distinguishes from sibling tools like create-draft-email and send-draft-email by emphasizing the one-step behavior, and the WRITE-operation framing separates it from read-only mail tools.

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 gives explicit routing guidance: 'Prefer create-draft-email + user review for report emails,' naming a concrete alternative and a condition that selects it. However, it does not state affirmative when-to-use scenarios beyond the implicit 'not for report emails,' so the guidance is clear but not exhaustive.

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