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 disclose the 'group counts only' output limitation, but it fails to disclose that the vast majority of its parameters are silently discarded after a shape check — behavior visible only by reading each parameter's description. Given an operation that fetches external resources, it also omits error behavior and what happens when robots.txt is missing or unreachable.

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?

A single efficient sentence with the output limitation front-loaded; no wasted words. It is appropriately short, though the brevity leaves major gaps that score low under other dimensions.

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 tool with 9 parameters, no output schema, and no annotations, this description is drastically incomplete. It does not explain which parameter selects the target robots.txt, what 'group counts' means precisely, what happens to the eight discarded parameters, or expected return/error behavior. An agent cannot confidently invoke this tool correctly with the information given.

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%, so the baseline is 3, but the descriptions actively mislead: parameters like ref, city, zone, json, and query all say they are 'discarded after the shape check', describing behavior that belongs to a completely different tool family (shape checks), not robots.txt fetching. Critically, no parameter description maps to the tool's stated purpose — 'url' says 'normalize or cite' and 'host' says 'public hostname', neither of which tells an agent which parameter supplies the robots.txt source. The description adds no clarifying meaning and fails to compensate for this mismatch.

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 states a specific verb+resource: 'Fetch a public robots.txt and return group counts only.' This is clear on its face and the 'group counts only' qualifier usefully scopes the output. However, it does not distinguish from siblings like web-fetch or fetch-status, and — more importantly — the stated purpose is not supported by the parameter list, which contains no parameter that clearly identifies which robots.txt to fetch.

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 guidance is given on when to use this tool versus alternatives. It never mentions siblings (web-fetch, fetch-status, browser-url-ok, domain-shape, etc.), provides no when-to-use / when-not-to-use conditions, and no prerequisites. An agent has no basis to select this over the other fetching/shape tools.

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