email_draft_list

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

No annotations are provided, so the description carries the full burden of behavioral disclosure, but it is silent on everything: whether this is read-only (likely, given sibling naming but never stated), pagination behavior, ordering, whether it returns full draft bodies or just metadata, or any failure modes. With zero annotations, the two-word description is insufficient behavioral context.

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 technically short, which is good, but at 4 words it is under-specified rather than concise. A useful listing tool description could add a sentence about scope and pagination without bloat. There is nothing actively wrong with the wording, but there is also no substance to reward.

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?

Given no output schema, no annotations, and 0% parameter coverage, this description is materially incomplete. It is a list operation on drafts (moderate complexity: likely paginated, account-scoped, returning multiple items), yet the description explains none of the return characteristics, filtering, or account requirements. For a 3-parameter tool with no structured support, this falls well short of minimum viable.

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 0%, so the description must explain the parameters, but it documents none of them. The limit and offset parameters are pagination-related, which an agent can infer from their names, but the description provides no confirmation of pagination semantics or explanation of accountId's role beyond being required. Sibling tools like email_search may offer similar parameters, leaving ambiguity about how they differ here.

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 'List email drafts' is a terse verb+resource statement but provides no scoping, filtering, order, or account context. It names the operation clearly but adds nothing beyond the tool name itself, making it barely distinguishable from the bare title. With dozens of email siblings, it fails to differentiate what 'list' returns (drafts only? saved vs unsent?) or how it relates to similar listing tools.

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?

No when-to-use guidance is provided. The description does not state when to prefer this over email_search, email_get, or email_get_thread for retrieving drafts, nor mention any prerequisites such as requiring a configured account before listing. The required accountId implies account context but the description never explains this dependency.

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