load_data

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

No annotations, so the description carries the full burden. It usefully discloses that the result includes shape, preview, summary and data, but says nothing about read behavior, memory/large-file handling, error cases for unsupported files, or how max_rows bounds the preview.

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?

One sentence, front-loaded with the action and formats, ending with the return payload. No wasted words, though the terseness contributes to the semantic gaps elsewhere.

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?

No output schema, no annotations, and 0% parameter coverage. The description partially compensates by naming the returned fields, but omits parameter behavior and file-handling caveats for a tool with a required path and two undocumented options.

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 coverage is 0% for three parameters. The description's format list loosely supports 'path', but 'column' (string-or-index selection) and 'max_rows' (default 20) are never explained, so an agent must guess their effect.

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?

Specific verb (load) plus the accepted file formats and the four things returned (shape, preview, summary, data). An agent can distinguish it from save_data and describe_file. No explicit sibling callout, but the purpose 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?

No statement of when to use this versus describe_file, analyze_dataset, or describe. Usage is only implied by the name and the data-oriented siblings. No prerequisites or exclusions are given.

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