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

With no annotations provided, the description carries the full behavioral burden. It discloses one useful trait: no browser is launched. But it omits other important behaviors, such as side effects (read-only?), return format, error handling, and how the additional parameters (ref, city, json, path) are processed. This is minimal transparency, not misleading but insufficient.

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, tightly crafted sentence that front-loads the action and immediately adds a crucial behavioral distinction. No words are wasted, and the structure makes the core purpose instantly clear. It is appropriately sized for the high-level information it intends to convey.

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 a broad, diverse schema (url, path, json, city, ref, feed, host) and no output schema or annotations, yet the description only covers the URL-checking aspect. An agent cannot infer how to handle the other parameters, what the tool returns, or what 'opened' means operationally. This creates a significant completeness gap despite the schema's individual parameter notes.

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 provides descriptions for all eight parameters, including notes like 'discarded after the shape check' and 'titles discarded,' so schema coverage is high. The tool description adds no parameter-level meaning, defaulting to the baseline score of 3. It neither enhances nor conflicts with the schema's explanations.

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 clearly states a specific verb ('Check') and resource ('whether a URL can be opened'), and the second clause 'No browser is launched' differentiates it from likely sibling browser-url-ok. However, 'can be opened' is imprecise about what exactly is checked (HTTP reachability, renderability, etc.), and the schema's non-URL parameters (json, city, path) are not reflected in the stated purpose.

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 explicit guidance is given for when to use this tool versus alternatives. The only context clue is 'No browser is launched,' which weakly implies a lightweight check, but it does not name sibling tools (e.g., fetch-status, browser-url-ok) or state exclusions. An agent must infer usage from the name and one behavioral clause.

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