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

With no annotations, the description carries the full burden of behavioral disclosure, and it does so meaningfully: each recipient consumes one unit of the daily allowance, and test_mode runs the full pipeline including content screening without sending or spending allowance. This goes beyond the schema's field descriptions. It does not describe error handling or the response shape, but the core side effects and dry-run semantics are explicit.

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?

The description is three short, front-loaded sentences: purpose first, then constraints and cost, then the test_mode workflow. There is no filler, no repetition of schema details, and no unnecessary complexity. Every sentence earns its place.

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 7-parameter mutation tool with no annotations and no output schema, the description manages to cover prerequisites, quota impact, and a safe testing workflow. It does not describe the response payload or explicitly link to get_sending_limits or verify_domain, but an agent still has enough guidance to invoke the tool correctly and avoid unintended sends.

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 86%, so the schema already documents most parameter formats. The description adds the crucial invariant that the from address must belong to the verified domain, clarifies that the to field can imply multiple recipients and that allowance is counted per recipient, and gives test_mode operational meaning beyond simply 'send nothing.' This is valuable semantic information not present in the schema alone.

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 opens with the concrete action 'Send a message,' which clearly identifies the tool's purpose, and the surrounding domain/from constraints confirm it is about email sending. No sibling tool performs sending, so there is no risk of confusing it with another operation. The resource is stated only generically as 'message' rather than 'email,' but the tool name and schema remove that ambiguity.

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 clear operating preconditions: the domain must be verified and the from address must belong to it. It also prescribes a workflow by telling the agent to run test_mode true first when building. It does not explicitly compare against sibling tools, but none of the siblings are sending alternatives, so no alternative routing is needed.

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