export_dataset

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

With no annotations provided, the description must carry the full burden of behavioral disclosure. It mentions two key behaviors: format inference from suffix and limiting to one source. However, it does not disclose whether the file is overwritten or appended, required permissions, or other safety-related traits. The description is adequate but lacks completeness for a mutation tool with no annotations.

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 extremely concise—only two sentences. It front-loads the core action in the first sentence and explains key parameters in the second. Every word contributes value; there is no redundancy or fluff.

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 the tool's low complexity (3 parameters, 1 required) and the presence of an output schema (though not detailed), the description adequately covers the main functionality. However, it omits details like file overwrite behavior and prerequisites, which would be useful for a file-writing tool. Still, it is reasonably complete for the use case.

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 schema has 0% description coverage, so the description fully compensates. It explains each parameter: output as a file path, fmt as 'parquet' or 'jsonl' with inference from suffix, and source as a filter to one source filename. This adds essential meaning and clarifies allowed values beyond the raw schema.

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 what the tool does: 'Write the per-page {source, page, text} dataset to a file (no vectors).' It specifies the exact action (write), the resource (per-page dataset), and the output (file). It distinguishes from siblings by explicitly noting 'no vectors' and the scope (per-page dataset), avoiding confusion with similar tools like import_dataset.

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 implicit guidance on when to use the tool by specifying 'no vectors' and 'no embedding,' which suggests this is for text-only exports. However, it lacks explicit when-to-use vs when-not-to-use statements or direct references to alternatives like import_dataset. The context is clear but not fully prescriptive.

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