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

Annotations only include the title, so the description carries the full burden. It states 'Read' which implies a read-only operation, but does not disclose whether it marks messages as read, requires special permissions, or behaves differently for missing/invalid ids. No contradictions with annotations, but minimal behavioral detail beyond the action itself.

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, front-loaded sentence with no fluff. Every word is purposeful, and it efficiently conveys the action, resource, and scope. It is appropriately sized for a tool with one parameter and no complex behaviors.

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 simple 1-parameter read tool with no output schema, the description covers the core action and parameter scope. However, given the abundance of sibling mail tools, it would be more complete if it explicitly differentiated itself (e.g., 'Use this when you have the message id and want a single message; use mail_search to find ids'). Return format and error behavior are not mentioned, but these are not strictly required without an output schema.

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% and the schema describes 'id' as 'Stored message id'. The description adds 'owned by the caller' which clarifies that the id must refer to a message belonging to the caller, a constraint not present in the schema. This adds meaningful context beyond the schema, improving parameter understanding.

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 'Read one stored message owned by the caller, by id' clearly specifies a verb (read), a resource (stored message), and a scope (owned by the caller, by id). It distinguishes from sibling tools like mail_search (searching) and mail_send (sending) by focusing on reading a single specific message owned by the caller. This is a precise and non-tautological purpose.

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 implies usage when you have the id of a message the caller owns, but it does not explicitly name alternatives or provide when-not-to-use guidance. There are many mail-related siblings (mail_read, mail_gmailread, mail_sources), yet the description offers no comparison. The context is clear but exclusions and alternative routing are absent.

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