send_message

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

Adds context beyond annotations: the send is immediate, a copy is stored in Sent, and user confirmation is expected first — meaningful for a non-idempotent, open-world mutation. It doesn't cover failure behavior, whether drafts are consumed on partial errors (that detail lives only in the schema), or attachment size limits.

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?

Four short sentences, front-loaded with the core action, then mode selection, then the safety precondition. No repetition of schema details and nothing wasted.

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 10-parameter, output-schema-less send tool with strong annotations and 90% schema coverage, the description covers the essential decision points (new message vs draft vs thread) plus the confirmation requirement. Missing only post-send/error semantics, which are low-value for selection.

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 90%, so the schema already documents draftId, replyThreadId, replyToMessageId, body/htmlBody, and attachments in detail. The description only restates the draft and threading modes at a higher level, adding no syntax or edge-case meaning beyond the schema. 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 verb and resource (sends an email immediately via SMTP, saves a copy in Sent), which cleanly separates it from create_draft. However, the threading instructions ('give replyThreadId or replyToMessageId') blur the boundary with the `reply` sibling, which the description never mentions.

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?

Gives concrete routing rules for two modes: send an existing draft via draftId, and thread via replyThreadId/replyToMessageId. It also adds a real safety instruction ('Confirm recipients and content with the user before sending'). It stops short of saying when to use `reply` or `forward` instead of this tool.

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