list_new_messages

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

The annotations only carry the safe-read profile; the description goes well beyond them by disclosing the per-account/per-label stored cursor, the first-call only sets the position, the ~1 week history expiry with date-based fallback, and drafts/spam/trash exclusion. The prompt-injection framing note (⟦mail:ID⟧ untrusted content) is behavioral context that no structured field provides.

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 purpose and the 'use get_message' pointer are front-loaded, and the stateful cursor explanation comes before the arg list. The Args block partly repeats schema defaults (INBOX, 20), though it earns its place by adding the 1-100 range and the ''-means-every-label rule.

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 an output schema exists, the description needn't explain return shapes, yet it still flags the more=true indicator. Combined with the stateful-cursor model, expiry fallback, exclusions, and untrusted-content warning, an agent has everything needed to call it correctly across calls.

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 0%, so the description must carry the parameters, and it documents all four: labelId semantics ('INBOX' default, '' = every label), pageSize range 1-100 with default 20 and the more=true leftover signal, startHistoryId's role versus the saved position, and advance's save-vs-peek behavior.

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 first sentence states a specific verb and resource with scope qualifiers: 'List the messages that arrived since the previous call (Gmail history), without bodies'. It also disambiguates from the sibling get_message ('use get_message to read'), so an agent can distinguish it from search_threads and get_message without opening either schema.

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 gives explicit conditions for the stateful options ('advance=false peeks', 'startHistoryId resumes from a historyId returned earlier') and routes reading to get_message. It doesn't contrast with search_threads for retrieving older or filtered mail, which is the main missing routing hint.

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