csv_schema

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

With no annotations, the description carries the behavioral transparency burden. It discloses that schema inference is done 'by sampling records', which is important for accuracy expectations, and specifies the return content (column names, types, nullability). It does not mention caveats about sampling accuracy or behavior with large files, but adds valuable context beyond the bare purpose.

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 a single, well-structured sentence that front-loads the verb and resource, and contains no filler or redundant 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?

The description covers the tool's purpose and return values, while the schema covers parameters well. It is somewhat incomplete in that it does not explain the varying output formats (inferred, json-schema, formatted) or discuss limitations of sampled inference, but for a mid-complexity tool this is a minor gap.

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 input schema provides full descriptions for all three parameters, giving 100% coverage, so the baseline is 3. The description's phrase 'by sampling records' aligns with the sampleSize parameter but adds no detailed semantics beyond what the schema already states.

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 uses a specific verb ('infer') and resource ('schema of a CSV file'), and notes the return values (column names, types, nullability). This clearly differentiates it from siblings like csv_sample or csv_stats, which focus on sampling rows or computing statistics.

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 implies the tool should be used when a schema needs to be inferred from a CSV file. However, it gives no explicit guidance on when to prefer this over alternatives like csv_inspect or csv_validate, and provides no exclusions or when-not-to-use context.

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