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

The annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the description must, and does, add real behavioral context: the result is a temporary file plus a download link. It does not disclose file lifetime/expiry, permission requirements, or rate limits, so it is not exhaustive. No contradiction with the write-and-create-a-file profile implied by readOnlyHint=false.

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?

A single sentence that front-loads the action and resource before the constraint and the return, with no filler. Every clause (cached, no rerun, formats, temp file + link) carries information.

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 simple two-required-parameter tool with no output schema, the description covers the action, both parameters, the accepted format values, and the return shape (temporary file and download link). Remaining gaps like link expiry and where data_ref originates are minor but not zero.

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% with no enums, so the description carries the full burden. It qualifies data_ref as "cached" (not an arbitrary id) and enumerates the accepted format values json or xlsx, which the bare schema does not provide. It does not describe the shape or provenance of data_ref further.

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 (Export), a specific resource (a cached data_ref), and the two output formats, plus the key scoping nuance that it does not rerun the query. It is clearly distinguishable from siblings like run_metric_data or run_statement, though it never names a sibling explicitly.

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?

"Without rerunning the query" implies the intended use case is reusing an already-computed result, which is useful context. However, it gives no explicit when-not guidance, no prerequisites (where a valid data_ref comes from), and no named alternative such as running the metric fresh instead.

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