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

With no annotations provided, the description carries the full burden. It discloses one behavioral trait: no browser is launched. However, it does not explain what 'check whether a URL can be opened' actually entails—does it make an HTTP request, validate syntax, or return a boolean? It also does not clarify the behavior for the many extraneous parameters, which appear to be discarded but are not explained. This leaves major behavioral gaps.

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 concise, one sentence, which is appropriately sized for a simple tool. However, it is under-specified: it omits critical details about the return value, the meaning of the many parameters, and usage context. The brevity is not a strength because it fails to convey the necessary information, so it sits at a 3 rather than higher.

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 tool has 9 parameters, no output schema, and no annotations, the description is severely incomplete. It only covers the URL check aspect, leaving the other parameters unexplained. There is no information about what the tool returns, how it handles errors, or when to use it. For a tool with this complexity, the description provides almost no context, making it inadequate for an agent to use correctly.

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 schema has 100% description coverage, so the baseline is 3, but the parameter descriptions themselves are confusing and not tied to the tool's stated purpose. For example, 'ref' is described as 'Git ref name; discarded after the shape check,' and 'city' is 'City name for a public weather hint; discarded after the call.' These suggest the tool performs other checks, but the description only mentions URL checking. The parameter descriptions add little value because they don't explain how they relate to the core function, and the tool description does not compensate for this misalignment.

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: 'Check whether a URL can be opened' and adds a key distinction: 'No browser is launched.' This gives a specific verb and resource. However, the input schema lists 9 unrelated parameters (city, feed, json, path, zone, etc.) with no explanation in the description, creating ambiguity about the tool's actual scope. The purpose is clear for the URL check but the schema suggests it might handle other checks, which is not addressed.

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?

No guidance is provided on when to use this tool versus alternatives. The description only states the basic function and the fact that no browser is launched, which hints at a lightweight alternative to browser-url-ok, but it never explicitly mentions sibling tools or selection criteria. There is no exclusion of cases where a browser is required or where other tools like fetch-status or normalize-url would be more appropriate.

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