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

With no annotations present, the description carries the full burden of side-effect disclosure. It reveals only that no browser is launched; it does not say whether the check performs network I/O, whether it is read-only, what it returns in failure cases, or how the various inputs are treated. This leaves the side-effect profile largely opaque.

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?

Two short sentences with no filler. The core purpose is front-loaded, and 'No browser is launched' earns its place as a key behavioral contrast.

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?

Despite a seven-parameter schema and no annotations or output schema, the description gives no guidance on how to choose among parameters, what 'can be opened' means, or what a successful or failed check looks like. It is too thin for the complexity of the input surface.

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 provides strong per-parameter descriptions (e.g., 'discarded after the shape check', 'JSON text to validate'), so the baseline is 3. The prose description adds no parameter-level meaning and, if anything, creates tension by focusing only on 'a URL' while the schema also includes host, path, city, and JSON.

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 first sentence names a specific action and resource ('Check whether a URL can be opened'), and the second adds a useful differentiator ('No browser is launched'). However, 'can be opened' is left ambiguous (HTTP status? syntax? network reachability?), and the input schema exposes six non-URL parameters (ref, city, feed, json, path), so the stated purpose does not fully match the actual input surface.

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 claim 'No browser is launched' implies a lightweight alternative to browser-launching tools such as playwright-url-ok, but it never names an alternative or states when to prefer this tool over fetch-status or normalize-url. Usage context is only implied, not explicit.

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