messages-export-csv

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

With no annotations provided, the description carries the full behavioral burden. It discloses two non-obvious behaviors: streaming pagination and returning a file URI rather than inline data. These tell the agent that the operation may be long-running, handles large result sets incrementally, and produces a file reference. It does not explicitly state that the operation is non-destructive, but 'export' strongly implies a read-only action, so this is a strong disclosure given the context.

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 three short clauses, front-loads the core action, and each sentence adds a distinct fact: the operation, the pagination behavior, the return format, and a pointer for constructing queries. There is no redundant wording or unnecessary detail, making it easy for an agent to parse quickly.

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 tool with five parameters and a complex query schema, the description plus the detailed schema covers most essentials. The mention of streaming pagination and file URI return addresses two important runtime aspects not obvious from the schema. Minor gaps remain, such as how the returned file URI is intended to be consumed (e.g., temporary link vs persistent file) and when the query-syntax prompt is available, but the presence of an output schema likely covers return-value details.

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%, with each of the five parameters (query, filename, maxItems, contentType, excludeThreadHistory) having a detailed description. Per the calibration baseline, this yields a 3 even though the description adds no parameter-level semantics. The mention of a query-syntax prompt is an external reference, not a substitute for the schema's own parameter documentation.

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 opens with a specific verb and resource: 'Export Gmail messages to CSV.' This clearly differentiates the tool from sibling tools like message-search or message-get because it specifies the operation (bulk export), the output format (CSV), and the return type (file URI). Even without naming siblings, the agent can confidently identify when this tool is the right one.

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 gives no explicit when-to-use guidance or comparison to alternatives. The only usage hint, 'Use query-syntax prompt for query reference,' directs the agent to external documentation for building queries but does not say when to choose this tool over message-search or message-get. The intended use case is only implied by the 'Export... to CSV' phrasing.

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