read_messages

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

With no annotations, the description carries the behavioral disclosure burden. It meaningfully warns that email content is untrusted third-party data and instructs the agent to treat it as data, not instructions. It also notes the max_results cap to keep output bounded, adding useful operational context beyond a bare read 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?

The description is concise and well-structured: purpose first, then selection semantics, then the critical security caveat. Every sentence adds necessary information without redundancy.

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 there is no output schema, the description adequately explains what is returned (full content, headers, plaintext body, attachment metadata), how selection works, the default cap, and the important untrusted-data handling. This is sufficient for an agent to use 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 description coverage is 100%, so the baseline is 3. The description adds value by clarifying the relationship between message_ids and query as alternative selection methods, and by explaining the output bounding behavior with max_results, which goes slightly beyond the individual parameter descriptions.

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 batch-reads full message content (headers, plaintext body, attachment metadata) in one call, which is a specific verb and resource. It also explicitly distinguishes itself from read_message by saying to use it instead of calling read_message repeatedly.

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?

It explicitly directs the agent to use this tool instead of calling read_message repeatedly, which is a clear usage signal. Selection via message IDs or a Gmail query is described, though it does not explicitly address when to prefer search_messages or other sibling tools.

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