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

Annotations already signal read-only, idempotent, non-destructive behavior; the description goes further by explaining newest-first ordering, pagination via next_page_token, thread/message grouping, and the summary fields returned. No contradiction with 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 front-loaded with the core action, quickly covers the key behavioral details, and closes with routing to alternatives. No filler; each sentence contributes distinct value.

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, 12-parameter list operation with a full output schema, the description sufficiently covers scope, ordering, pagination, grouping semantics, and alternatives. Remaining details are already carried by the input schema and annotations.

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%, so parameters are already documented. The description adds useful meaning around pagination (returned next_page_token for subsequent calls), default ordering (newest first, relevant to the ascending parameter), and the semantic difference between paging and searching.

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?

States a specific verb ('Lists'), resource ('conversation threads'), and scope ('in one inbox'), along with default ordering ('newest first'). This clear scope distinguishes it from sibling tools like get_agentmail_threads and get_agentmail_inbox_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?

Explicitly says to use get_agentmail_inbox_messages when individual messages are needed and get_agentmail_inbox_threads_search when querying rather than paging. The description leaves no ambiguity about when this page-oriented, thread-list tool is appropriate.

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