send_mail

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

No annotations are supplied, so the description carries the full behavioral burden, and it does meaningful work: it discloses that the action is irreversible and that large attachments are uploaded in chunks with a failure-abort semantic ('if an upload fails nothing is sent'). It omits permission requirements, the effect of saveToSentItems, and anything about what is returned (e.g., a message id), which are relevant for an 8-parameter 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?

Three short sentences, no filler. The primary action and its irreversibility are front-loaded, and the attachment edge case follows as secondary detail, which is the right ordering for an agent scanning the definition.

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, 8-parameter tool with no annotations and no output schema, the description covers the two things an agent most needs: that the send is irreversible and how attachment uploads behave on failure. The remaining gap is return-value expectations and the semantics of saveToSentItems, which are not covered here or anywhere in structured fields.

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 50%, and the description adds meaning mainly for attachments by restating the 3 MB threshold and the 150 MB ceiling also present in the schema property description. The remaining parameters (cc, bcc, subject, body, bodyType, saveToSentItems) receive no added explanation, such as whether bodyType defaults to text or what happens when saveToSentItems is omitted.

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 ('Send an email immediately'), which clearly distinguishes it from prepare-only siblings like create_draft. It does not explicitly name sibling alternatives such as reply_message or forward_message, so an agent must infer that this tool is for new mail composition rather than replies or drafts.

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?

Use is strongly implied by 'immediately' and by the irreversibility warning, which tells the agent this is the terminal send step rather than a draft step. However, there is no explicit guidance such as 'use create_draft to compose first' or 'use reply_message to respond to an existing thread', leaving the routing decision to inference.

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