export_query

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

With no annotations, the description carries the full burden and does reasonably well: it discloses read-only semantics, that no row limit is applied, the default output location, accepted formats, and that a 5-row preview is granted only for AI-allowed sources. It omits overwrite behavior, permission requirements, and whether the filename needs an extension.

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?

Three compact sentences, front-loaded with the core action. The 'fmt: csv, parquet or xlsx' fragment is terse but slightly choppy against the prose around it.

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?

An output schema exists, so return values need not be described, yet the description still summarizes them (path, row count, columns) without harm. Remaining gaps are minor operational details such as overwrite behavior and filename format conventions.

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 compensate. It adds value for `fmt` by enumerating csv, parquet, and xlsx, and clarifies `sql` is a read-only SELECT, but `filename` gets no guidance (path vs. name, extension handling) beyond the default folder mention.

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 gives a specific verb and resource: run a read-only SELECT and save the result to a file. It implies the distinction from the sibling `query` tool by emphasizing persistence to the output folder and no row limit, but it never names `query` explicitly, so the differentiation is inferred rather than stated.

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?

Usage is implied ('no row limit', 'save it to the output folder') which suggests this is for large result sets the agent wants persisted, but it never states when to use this over `query` or `check_availability`. No exclusions or prerequisites are given.

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