send

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

Adds meaningful behavior beyond annotations: the message is copied to Sent, sending is conditional on server permissions and allowed recipients, and draft is the fallback. Annotations already cover the destructive/non-idempotent/open-world profile, so the description need not repeat those traits.

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 compact sentences with the main action and constraints front-loaded. Every clause contributes useful routing or behavioral information without 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 destructive send operation with rich annotations and fully documented inputs, the description covers the key operational constraints, side effect, and alternative tool. No output schema exists, and the agent has enough context 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?

Schema description coverage is 100%, so the schema already documents all six parameters, including reply metadata, recipients, and body formatting. The description adds no additional parameter semantics beyond what the schema provides, so baseline 3 is appropriate.

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 action and resource: sending a message over SMTP and copying it to Sent. It also distinguishes itself from the sibling draft tool by naming draft as the fallback when sending is not allowed.

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?

Explicitly gives the conditions for use: the server must allow sending and recipients must be allowed. It also names the alternative tool, draft, for the otherwise case, leaving little inference needed.

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