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 not state that fetching a public URL might fail, that the tool only counts groups and does not return the full content, what happens on redirects or network errors, or whether the tool is a read-only operation. The word 'Fetch' implies a network read, but nothing clarifies the tool's behavior beyond the bare action. The biggest gap: the tool accepts a JSON parameter, a zone parameter, and a host parameter that seem irrelevant to fetching robots.txt, and the description does not explain what happens to them.

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?

One sentence, no filler, front-loaded with the verb and resource. However, the single sentence is too terse to do its job — it states the minimum verb phrase without context that would justify its length. Concise but not complete.

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?

This tool has 4 parameters, no annotations, and no output schema. The description must compensate for all of that, and it does not. It does not say what the output looks like, which parameters matter, how to handle failures, or when to prefer it over a sibling. For a network operation with multiple unrelated-looking parameters, this is inadequate.

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%, but the description adds zero value for parameters. The parameter descriptions themselves are weak ('HTTPS URL to normalize or cite', 'Public hostname', 'JSON text to validate; discarded after the check', 'IANA timezone name') and the tool description does not clarify which parameters are actually relevant for fetching robots.txt or how they interact. For a network fetch tool, the description should at least map the parameters to their role in the fetch. It does not.

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 says 'Fetch a public robots.txt and return group counts only.' It uses a specific verb and resource, but the title 'inspect-robots' is nearly identical in meaning, so the description adds little beyond the name. It also does not distinguish this tool from its siblings or clarify what 'groups' means (user-agent groups? crawl-delay groups?), leaving ambiguity.

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, no scenarios, no exclusions, and no mention of what not to use it for. The description simply states the action with no context for an AI agent to decide if this is the right tool. With no annotations and no sibling differentiation, the agent must guess.

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