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

Beyond the annotations, the description discloses material behavior: cold-outreach checking, possible account pausing, the AI-assistant disclosure line unless by_person is set, attachment and recipient limits, exact cost structure, and that failures are not charged. These are important operational consequences an agent cannot infer from the schema or annotations.

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 dense but front-loaded: it opens with the core action, then layers threading, attachments, recipient limits, policy, disclosure, and cost. The cost sentence is long but useful. It could be split for readability, but no sentence is clearly 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 9-parameter mutation tool with low schema coverage and no output schema, the description covers the critical behavioral context: limits, policy enforcement, AI disclosure, and pricing. Minor gaps remain around cc/html/subject and the success response, but the essential decision and invocation context is present.

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?

With only 22% schema description coverage, the description compensates for most important parameters: inbox, to-recipient cap, reply_to_message_id threading, attachments from the file store with size/file limits, by_person behavior, and text usage for download links. It does not explicitly explain cc, html, or subject, but those are comparatively self-evident.

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 states a specific verb and resource: 'Send from one of this account's inboxes.' It also clarifies threading and attachment behavior, so the core action is unambiguous. It does not explicitly distinguish itself from sibling mail tools such as google_mail_send or m365_mail_send, which keeps it from a 5.

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 gives explicit when-to-use guidance ('For support, operations and replies, not cold outreach'), states hard limits ('at most 20 new addresses a day'), describes enforcement ('the third within 7 days pauses the account's email'), and names an alternative for large files ('Big files are cheaper as a download link (files_get)'). This is unusually complete routing and policy guidance.

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