validate_dataset

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

With no annotations the description must carry the burden; it does disclose the return shape (severity, stable code, hint, 0-100 score) which is valuable since no output schema exists. It never states that the operation is read-only/non-destructive, whether it writes a report artifact, or how expensive a full run is.

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?

Two dense sentences, front-loaded with the verb and check list, then the return contract. No filler or redundant restatement.

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 3-param, read-only validator with no output schema, the enumeration of checks plus the description of returned issues and score is close to sufficient. Missing only prerequisites and the validate-vs-report relationship to sibling tools.

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?

At 67% schema coverage the schema explains checks and include_frames, and the description's list of check categories (metadata, vocabulary, episode indices/lengths, fps, layout) indirectly tells the agent what values the checks array accepts. It adds nothing about the required path parameter or the format expectations behind it.

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?

States a specific verb (Run structural validation) and enumerates the concrete checks performed, which is far more than a restatement of the name. It does not differentiate itself from overlapping siblings such as quality_report or detect_dataset, so an agent still has to infer the boundary.

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 quality_report/detect_dataset, no prerequisites (e.g. must path already be catalogued or converted), and no guidance on cost. The only usage hint ('omit for defaults') lives in the schema, not the description.

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