list_messages

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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint), the description adds valuable behavioral details: it queries Microsoft Graph or IMAP, treats email content as untrusted data (security caution), and returns [] for unknown folders or missing accounts. It also clarifies that bodies are excluded. This significantly enriches behavioral understanding.

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 concise, front-loaded with the main purpose and output format, then adds critical caveats (no bodies, untrusted data, empty result behavior). Each sentence adds value and the structure is logical and easy to parse.

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 the output schema exists, the description does not need to detail return types but still lists the summary fields. It covers error behavior ([]), security (untrusted data), and alternative for bodies. It also provides folder guidance. For a list tool with annotations covering safety, this is fully complete.

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 100%, with each parameter (top, skip, folder, account_id) already described. The tool description repeats the folder options (inbox, sent, drafts, etc.) which are also in the schema, and does not add new semantics beyond the general purpose. Since the schema fully documents parameters, a baseline of 3 is appropriate.

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?

Clearly states the verb (List), resource (messages in a mailbox folder), ordering (newest first), and the exact output shape (summaries with listed fields). It also differentiates from read_message by explicitly excluding bodies, and from list_unread by indicating folder-based listing. The purpose is unambiguous.

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?

Provides a clear 'when not to use' instruction: bodies are not included, so use read_message with the returned id. It also notes the empty-array return for unknown folders/missing accounts, which helps in error handling. However, it does not explicitly compare with list_unread or search_mail, though the intended use case is evident from the description.

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