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. 'Return group counts only' hints at output shape but does not explain what 'group counts' means, whether the robots.txt is fetched live or validated, which parameter carries the target URL, or how the discarded parameters behave. For a tool with zero annotation coverage, this is a significant disclosure gap.

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?

The single sentence is short with no filler, which is structurally clean, but it is under-specified rather than concise. It omits the crucial mapping between the tool purpose and the parameters, so the brevity costs completeness. The one informative clause, 'return group counts only,' is front-loaded, but that does not compensate for the absent parameter guidance.

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 9-parameter tool with no annotations, no output schema, and no enums, the description is severely incomplete. It does not specify which parameter receives the robots.txt URL, what the returned 'group counts' look like, or what happens with the other eight parameters. Given the tool's complexity and the absence of structured fallback, this definition is inadequate for correct invocation.

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?

While schema coverage is 100%, the description adds no parameter meaning and fails to bridge the stated purpose to any parameter. It never indicates that 'url' or 'host' is the robots.txt input, so despite the high schema coverage, the description actively leaves the agent guessing which of 9 params drives the fetch. The mismatch between the declared purpose and the unrelated 'discarded' params (city, json, zone) makes the parameter semantics actively misleading.

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+output ('Fetch a public robots.txt and return group counts only'), but this purpose is undermined by the input schema: 7 of 9 parameters (ref, city, json, path, zone, query, feed) are described as 'discarded' or unrelated to robots.txt fetching. Only 'url' and 'host' plausibly map to the stated purpose, and even those are labeled ambiguously ('URL to normalize or cite'). The stated purpose is clear in isolation but misleading against the schema, and it does not differentiate this tool from the 28 shape-check siblings.

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?

There is no guidance on when to use this tool versus alternatives. With 28 sibling tools, several of which are shape/URL checkers (domain-shape, figma-url-shape, browser-url-ok), the description offers no condition, exclusion, or alternative. An agent has no basis to choose inspect-robots over web-fetch or fetch-status.

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