list_drafts

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

No annotations are provided, so the description carries the full burden. It usefully discloses the shape of each returned summary row and that bodies/attachments are excluded, but it never states read-only safety, pagination behavior, or default page size for a list operation.

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?

Two sentences, no filler, and the returned-field summary is front-loaded before the sibling routing. Every clause supplies something an agent can act on.

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 and no annotations, the description partially compensates by enumerating the returned fields and directing deep reads elsewhere. It stops short of noting pagination semantics or the default for max_results, which matters for a paged list tool.

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 coverage is 67%: query and page_token are described in the schema, max_results has bounds but no description. The description adds no parameter-level meaning (no query syntax notes, no page-size guidance), so the schema remains the primary source.

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 (Gmail drafts) plus the fields returned (recipients, subject, snippet, has_attachments), which sharpens the concept beyond a bare listing. It also names the sibling read_draft so an agent can distinguish shallow listing from full retrieval.

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 read_draft for the full body and attachment list, and reuse the returned draft_id with update_draft. That supplies both the alternative and the condition that selects it, leaving nothing to inference.

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