Poll for new mail

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

The description reveals non-obvious stateful behavior: the first poll only records the mailbox position and returns nothing, and polling never marks messages as read. This goes beyond the annotations, which only indicate non-read-only, open-world, non-idempotent, non-destructive. The behavior about not replaying backlog is critical for correct usage.

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 two sentences, front-loaded with the core purpose, and every sentence adds value (behavior on first poll, read side-effect). No filler or repetition. It is optimally concise for the amount of useful information conveyed.

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?

With no output schema, the description states 'Messages that have arrived' but not the exact format. However, it covers the essential contexts: first poll behavior, statefulness, and read side-effects. The 'advance' parameter and its relation to ack_folder are in the schema, so the description doesn't need to repeat that. Overall, it's complete enough for a polling tool, just missing explicit output shape.

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?

The input schema already provides descriptions for all three parameters (limit, folder, advance) with 100% coverage. The tool description adds no extra parameter-specific information. Per the rubric, the baseline is 3 when schema coverage is high, which is exactly the case here.

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 that the tool emits messages arriving since the last poll, with a specific initial behavior. It distinguishes itself from sibling tools like search_mail and get_headers by focusing on incremental new-message retrieval. The title confirms the action, and the description adds the crucial 'first poll emits nothing' detail.

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 for polling new mail and explains the first-call behavior, but it does not explicitly contrast with alternatives like search_mail or folder_status. There's no 'use this when' or 'instead of' guidance. While the context is clear, explicit alternatives or exclusions are missing.

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