CSV Import Rehearsal

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

Annotations already mark this as read-only, idempotent, and non-destructive, and the description adds valuable context: it never writes an import destination, costs 0.03 USDC per completed bounded job, and returns specific result categories. This goes beyond the annotation hints without contradicting them.

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 two sentences with no filler. The primary action is front-loaded, the result payload is summarized efficiently, and the cost/side-effect guarantee are useful additions placed at the end.

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 no output schema, the description usefully names the exact categories of returned results and states the non-persistent behavior. It still leaves some ambiguity around what 'bounded job' means and how malformed CSV is handled, but the core selection and invocation context is clear.

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 parameter meaning. It only broadly references 'csv' and a 'typed column contract' (columns), but does not explain delimiter, allow_extra_columns, or the precise format expectations for csv. The schema provides structure, but the description adds limited parameter-level value.

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 a specific verb and resource: simulate a CSV import against a typed column contract. It enumerates exact outputs—accepted rows, rejected rows, proposed normalizations, and formula-risk cells—and explicitly distinguishes this from a real import by noting it never writes to an import destination.

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 usage context is implied by the name and wording: use this as a safe rehearsal before a real import, since it never writes. However, there are no explicit when-to-use/when-not-to-use instructions and no alternatives are mentioned, so the guidance is only implicit.

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