summarize_dataset

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

With no annotations, the description carries the full burden; it does well on response contents (it lists the returned fields, which is the key behavioral fact for a read tool). It omits read-only confirmation, requirements on `path` (local dataset root vs file), behavior on unsupported/invalid datasets, and cost when episode rows are included — that last point lives only in the schema.

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, zero filler, with the highest-value content (the field list) front-loaded and the usage cue trailing as an imperative. The dense enumeration earns its length because no output schema exists.

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 exists, so the description must explain returns — it does so thoroughly via the field enumeration. The only real hole is the undefined `path` argument, which is important for correct invocation but is the sole 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?

Schema description coverage is 50%: `include_episodes` is documented ("can be long") but `path` has no description anywhere — the description never says what it points to. The description adds no parameter meaning at all, so it fails to compensate for the 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?

States a specific verb (summarise) and resource (dataset) and enumerates exactly what the summary contains: format, version, fps, robot type, feature metadata, episode count, frames, duration, tasks, notes. This implicitly distinguishes it from validate_dataset or quality_report, but no sibling is named, so it falls short of the 5 bar.

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 when-to-use trigger. It does not state when to prefer siblings like detect_dataset or validate_dataset instead, nor any prerequisites, so it is strong context without exclusions.

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