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

Beyond the readOnlyHint/idempotentHint annotations, the description reveals key behavioral traits: empty pages do not mean zero emails unless no filter is applied; IMAP pages are capped at 50 live messages; limiting to 20 avoids runtime timeouts; and IMAP email IDs change on move/update, so reuse the latest ID. These are essential for correct usage and go well beyond annotation defaults.

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 lengthy but every sentence provides actionable detail: workflow, date format, counting caveats, pagination limits, and ID handling. It is front-loaded with the core purpose and workflow, then deepens into edge cases. While it could be tightened, the density of useful information justifies its length; nothing is filler.

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 tool with no output schema and low schema coverage, the description covers the most critical aspects: workflow, date semantics, counting, pagination limits, folder_id acquisition, and ID mutability. It does not explicitly explain to, from, any_email, or cursor, but those are simpler and likely self-evident or covered by schema descriptions. Overall, it provides sufficient context for an agent to call the tool correctly.

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 only 33%, so the description carries the burden of explaining parameters. It specifies after/before as ISO 8601 UTC datetimes with a 'today' hint, advises a small limit (20) to avoid timeouts, and details how to obtain folder_id (via email_list_folders -> folder.id) and the distinction from human names. It also explains the email provider ID behavior for related tools, adding context that is not in the schema.

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 opens with a precise statement of the tool's function: 'List messages inside one exact folder.' It specifies the resource (folder) and the operation (list messages), and provides a concrete workflow (list folders -> select folder.id -> list messages -> email.id -> read/action). This clearly distinguishes it from siblings like email_list_messages (which likely lists across folders) and email_list_folders (which lists folders, not messages).

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 gives explicit when-to-use guidance: for listing messages in a specific folder after obtaining a folder ID via email_list_folders. It also tells when NOT to use it: for totals, use folder.total_count/unread_count from email_list_folders instead. It does not explicitly name email_list_messages as an alternative for cross-folder listings, but the folder-specific workflow implies the distinction. This is clear and practical.

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