list-mail-attachments

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds value by clarifying that the tool returns metadata only, not content bytes, and explains the /$value suffix for raw bytes and the risk of truncation with embedded contentBytes. This is behavioral info beyond annotations.

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 a single clear sentence followed by a concise tip. It front-loads the action and places the alternative usage in a separate tip block. All sentences serve a purpose; no fluff. It could be slightly tighter, but it's well-organized.

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 read-only list tool with a rich schema covering pagination and filtering, the description covers the main use case and gives crucial guidance on downloading bytes. It doesn't describe the response structure, but there's no output schema and the fields are listed in the tip. It's sufficient for an agent to call 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 description coverage is 100% and each parameter already has a detailed description (top, skip, filter, etc.). The description does not add new parameter-level details beyond the schema, which is acceptable given the high coverage. The tip mentions a path suffix but not a parameter directly. Baseline 3 applies.

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 retrieves a list of attachment objects for a message, and enumerates the fields returned (id, name, contentType, size, isInline). This distinguishes it from siblings like list-mail-messages or add-mail-attachment. The scope is explicit: attachments on a specific message (via required messageId).

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 tip explicitly routes download intent to download-bytes with a concrete URL pattern, and warns about truncation when using the bare attachment URL. This gives a clear alternative for a common follow-up action. However, it doesn't broadly contrast with other siblings (e.g., listing all mail vs. attachments), but the tool name and parameter make that self-evident. The guidance is useful and explicit for the key alternative.

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