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

With no annotations, the description does real work: it discloses that the draft retains its original wording while the sent message keeps what actually left, so the two remain comparable. It omits whether sending is irreversible, whether the draft is removed afterward, and any permission requirements, which are meaningful gaps for a send mutation.

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 with no repetition of schema content. The closing clause ('so the two stay comparable afterwards') is slightly opaque but still earns its place by explaining the persistence semantics.

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 send mutation with no annotations and no output schema, the description covers the draft/body relationship but says nothing about what comes back, error behavior, or send irreversibility. It is adequate but leaves an agent guessing on important post-condition details.

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 100% and the schema already documents body, status, draft_id, and the attachment forms in detail. The description adds only marginal context about the body field ('the text as given in body when you edited it'), 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 gives a specific verb+resource ('sends a draft to the contact') and clarifies the body-override mechanic. It does not, however, distinguish this from nearby siblings like send_email or reject_draft, so an agent must infer the difference from the name alone.

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?

It implies when the body override applies ('when you edited it') but never states when to choose this over reject_draft, send_email, or delete_compose_draft. Usage context is only implied.

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