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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does state a key limitation: 'return group counts only' implies the tool does not return the full robots.txt content. But it gives no information about network behavior (redirects, timeouts), error handling, whether the URL must be public, or what happens if the robots.txt is missing. This is minimal transparency but not contradictory.

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 description is a single, efficient sentence with no wasted words. It front-loads the action and result. The only structural downside is that it omits any mention of the target parameter, leaving an important gap despite the concise phrasing.

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?

Given the 8-parameter schema with many unrelated fields, no annotations, and no output schema, the description is not sufficiently complete. It fails to explain how the parameters map to the robots.txt fetch, what 'group counts' means, or what fields appear in the response. An agent with this definition would likely struggle to construct a valid invocation. The phrase 'return group counts only' plus the confusing parameter list leaves too many unresolved questions.

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?

The input schema does provide descriptions for each parameter, so schema coverage is high, but those descriptions are largely unrelated to the stated purpose. For example, 'City name for a public weather hint; discarded after the call' and 'JSON text to validate; discarded after the check' have nothing to do with fetching robots.txt. The description adds no parameter guidance, so an agent cannot tell whether to populate 'url', 'host', or 'path' to specify the robots.txt source. The schema's per-parameter descriptions are present but misleading for the core function, so the description does not meaningfully compensate.

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 is a single clear sentence: 'Fetch a public robots.txt and return group counts only.' It names a specific verb ('fetch'), a specific resource ('robots.txt'), and a specific output ('group counts only'), which distinguishes it from generic fetch tools like web-fetch. However, the input schema lists 8 parameters (ref, url, city, feed, host, json, path) none of which is obviously the robots.txt location, creating ambiguity about what the tool actually operates on.

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 such as web-fetch, fetch-status, or normalize-url. The description does not state conditions like 'use this when you need just the group counts from a robots.txt file' or mention when not to use it. The sibling list contains multiple fetch/normalize tools, so the absence of any such direction forces the agent to infer usage from the name and description alone.

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