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

Annotations only declare readOnlyHint, so the description adds real value: it names the required scope (gmail.compose) and discloses that accounts missing it are surfaced in `errors` with a reconnect hint. This is useful auth/error behavior beyond the annotation, though pagination and full error shape aren't described.

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?

A single dense sentence that front-loads the purpose, then folds in the return fields, the content alternative, and the auth/error behavior. No filler; every clause earns its place.

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?

With no output schema, the description compensates by enumerating the returned fields (id, message id, thread id) and stating no body is included, plus auth and error handling. Nothing an agent needs to call this correctly is missing.

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% (both `limit` and `accounts` are documented in-schema), so the baseline is 3. The description reinforces the `accounts` subset semantics but adds no syntax or format detail beyond what the schema already provides.

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 (List) and resource (draft ids across draft-capable Gmail accounts), and immediately distinguishes itself from content-retrieval siblings by noting get_draft/get_thread are needed for bodies. An agent can tell exactly what this returns without opening any schema.

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 routes the agent: use this for ids only, and call get_draft or get_thread with the thread_id when content is needed. It also tells when the `accounts` subset applies. Lacks a formal when-not clause, but the alternative and its trigger condition are clear.

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