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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context by explaining the draft.id field's role in subsequent operations and warning that it is not email_id or subject. This enriches the annotation-covered core without contradicting it.

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 three short sentences with no filler. The primary purpose is stated first, followed by the key output-field caveat. It is efficient and front-loaded, though it could have been even more structured by grouping the draft.id clarifications into one sentence. Overall, it 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?

The tool has no output schema, so the description should compensate for return-structure details; the draft.id clarification helps but leaves the rest of the return object unspecified. The description also omits any explanation of the limit and any_email parameters, which are left to schema (limit has none) and guesswork. Given the complexity of 4 params and no output schema, the description is adequate but incomplete.

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 only 50% (limit and any_email lack descriptions). The tool description does not compensate; it mentions no parameters at all. Cursor and account_id are described in the schema, but limit and any_email remain ambiguous. The description's note about draft.id concerns output, not input parameters, so it does not help an agent understand the meaning or usage of any_email or limit.

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 clearly states the tool lists email drafts with a specific verb and resource. It also adds a crucial distinction: the returned draft.id is the identifier for subsequent get/update/send/delete operations, and clarifies it is not email_id or subject. This distinguishes it from sibling tools like email_list_messages and prevents misuse of the returned ID.

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?

The description provides no explicit guidance on when to use this tool over alternatives such as email_list_messages, nor does it state any exclusions or prerequisites. The only implication is that this is for drafts, but it doesn't clarify whether email_list_messages includes drafts or when to prefer one over the other. There is no mention of the account_id requirement for users with multiple accounts (even though the schema describes it, the description doesn't reference it).

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