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

With no annotations at all, the description carries the full burden of behavioral disclosure. It only says it fetches a public robots.txt and returns group counts, but does not disclose that it performs network I/O, discards most parameters, or that it is read-only. The schema parameter descriptions do mention 'discarded', but the description itself remains silent on side effects and operational traits. An agent cannot anticipate that passing a 'city' or 'json' parameter might be discarded, or that the tool might not even touch robots.txt for some inputs.

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 fluff. It states the action and the result in a front-loaded manner. This is maximally concise and structurally straightforward.

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?

The tool has 9 parameters, no required fields, no output schema, and no annotations. The description only explains one narrow use case (robots.txt) while the schema suggests a broader multi-purpose shape-checker. This leaves significant gaps: which parameter to use for what, what 'group counts' means, how results are returned, and whether the tool handles the other parameter types. Given the complexity, the description is grossly underspecified 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?

Schema description coverage is 100%, so each parameter is already described in the schema (e.g., 'HTTPS URL to normalize or cite', 'Git ref name; discarded after the shape check'). The description adds no meaning about how parameters map to the intended robots.txt action—for instance, it does not specify which parameter should hold the robots.txt URL, nor how 'group counts' relate to any parameter. With high coverage, the baseline is 3, and the description fails to add value beyond that, so 3 is appropriate.

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 action: 'Fetch a public robots.txt and return group counts only.' This is a clear verb+resource. However, the input schema contains 9 parameters (ref, city, feed, json, path, zone, etc.) with descriptions like 'discarded after the shape check' and 'City name for a public weather hint', which suggest the tool performs multiple shape checks far beyond just robots.txt. The description does not capture this breadth, making it misleading about the tool's actual scope. It does partially distinguish from siblings by naming robots.txt, but the mismatch with the schema lowers clarity.

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?

The description provides no guidance on when to use this tool versus the many sibling tools (domain-shape, jira-key-shape, validate-json, etc.). There is no mention of alternatives, exclusions, or conditions that would route an agent to this tool. The schema hints that this tool is a generic shape-checker (all params are 'discarded' after a check), but the description says nothing about that broader role, leaving the agent without any usage context.

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