summarize_dataset

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered by structured data. The description adds genuine value beyond that by enumerating the returned content — important because there is no output schema — and by framing the tool as a pre-analysis inspection step. It does not disclose cost, failure behavior on an invalid path, or output size, keeping it at 4.

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 sentences, front-loaded with the verb and the full field inventory, with the usage cue placed at the end. The field list is long but earns its place because no output schema exists. Minor redundancy in listing both 'episode count' and 'frames'/'duration' is acceptable.

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 two-parameter read-only inspection tool with no output schema, the description covers what comes back reasonably well. However, the single required parameter's meaning (what kind of path) is left entirely undefined, and nothing is said about behavior on an unreadable or non-dataset path — a real gap for the one input the agent must supply.

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 only 50%: 'path' has no description at all, and the description never clarifies whether it is a filesystem path, a dataset directory, or a catalog identifier. 'include_episodes' is documented only in the schema ('can be long'), and the description does not mention it or its cost tradeoff, so it fails to compensate for the coverage gap.

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+resource ('Summarise a dataset') followed by an explicit enumeration of the fields surfaced (format, fps, robot type, features, episodes, frames, duration, tasks, notes). That makes the tool's output scope unmistakable. It does not name a sibling such as detect_dataset or quality_report to differentiate itself, so it stops short of a 5.

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?

'Use before any analysis to learn the schema' gives a clear, actionable trigger for calling this tool first. There are no explicit exclusions or named alternatives (e.g., when to prefer detect_dataset or validate_dataset instead), which keeps it below a 5.

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