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

Annotations already declare the tool read-only, idempotent, safe, and non-destructive. The description adds one useful behavioral trait—no browser is launched—but fails to disclose whether a network request is made, whether it validates only the shape of inputs, or how discardable params are handled. It is not contradictory with the annotations, but it does not fully compensate for what annotations do not cover.

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 two short sentences with no filler, and the core message is front-loaded. The brevity is not itself a problem, though it does contribute to the ambiguity in 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?

Given a 7-parameter schema with no required fields, no output schema, and many similar sibling tools, the two-sentence description is not enough. It does not explain what the tool returns, whether it performs a real open/check or a shape-only check, or how to interpret the non-URL parameters. An agent would struggle to invoke it correctly beyond the most obvious url case.

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 description only addresses 'a URL' and provides no meaning for the other six schema parameters (ref, city, feed, host, json, path). With schema_description_coverage reported as low and 7 parameters, the description should clarify how these fields factor into the operation, but it leaves them unmentioned. The individual schema descriptions are actually more informative than the main tool description for most parameters.

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 clear action and object: 'Check whether a URL can be opened' and adds a relevant caveat that no browser is launched. However, it does not clarify whether this is a network reachability check or a shape/format check, and the input schema exposes seven unrelated parameters (ref, city, feed, json, path), which makes the actual purpose ambiguous. It differentiates from playwright-url-ok but not from fetch-status or web-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?

The only usage hint is 'No browser is launched,' which implicitly excludes browser-driven tools but does not say when to choose this tool over siblings like fetch-status, web-fetch, normalize-url, or playwright-url-ok. No alternatives are named, and there is no guidance about which of the many schema fields should be supplied for which scenario.

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