convert_csv_to_parquet

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does mention snappy compression and a fixed cost (0.015 USDC), but it fails to explain how the CSV data is passed (via payload string? JSON? path?), what happens when paymentSignature is missing, or any side effects. For a tool with no annotations, this is a significant gap.

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 sentence, front-loaded with the main action and format, and includes a brief cost note. It is efficient, but the phrase 'cutting query costs and storage by 85%' is an unsubstantiated promotional claim that adds noise rather than essential information. Still, it is concise and structured well.

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 conversion tool, it is critical to know the exact input format (raw CSV, base64, JSON config) and payment requirements. The description states the output format but omits how the payload should be structured, what limits apply, and how the paymentSignature interacts with execution. With no output schema and no annotations, this leaves agents guessing on essential call details.

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 100% as both parameters have descriptions, though generic ones. The description adds context that the input is 'delimited CSV/TSV data' and output is 'Apache Parquet', but it does not clarify how the payload parameter should encode that data (raw string vs. JSON object). This aligns with the baseline for full schema coverage, adding marginal value only.

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: 'Converts delimited CSV/TSV data into columnar Apache Parquet format with snappy compression.' This distinguishes it from sibling conversion tools like convert_yaml_to_json_safe or convert_svg_to_png, which handle different input/output formats. The intended transformation is unambiguous.

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 usage: convert CSV/TSV to Parquet for cost and storage efficiency. However, it does not explicitly state when to choose this tool over alternatives, nor does it mention any exclusions or conditions. There is no reference to sibling tools or 'use this when' guidance, leaving the context to be inferred.

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