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

The description discloses one behavioral aspect—that query and fragment are dropped—but does not explain other behaviors such as whether it returns an object or string, how invalid URLs are handled, or if any network calls are made. With no annotations to supplement this, the description falls short on transparency.

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 extremely concise—two short sentences that convey the main purpose and a key behavior without any unnecessary elaboration. It follows a clear and efficient structure.

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 description is incomplete in the context of the provided schema. It does not reconcile the presence of eight additional parameters with the stated behavior, nor does it explain what the tool actually does with inputs like 'city' or 'query'. There is no mention of output format or error handling, leaving an agent without enough information to reliably invoke the tool.

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 descriptions for parameters like 'city' ('City name for a public weather hint') and 'ref' ('Git ref name; discarded after the shape check') are clearly irrelevant to URL normalization and appear to be copy-pasted from other tools. The description does not clarify that only the 'url' parameter is meaningful or that the others are ignored, leaving the parameter semantics confusing and unhelpful.

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 the core action: returning origin, host, and path for a URL, and dropping query and fragment. However, the presence of many unrelated parameters in the schema (e.g., 'city', 'feed', 'ref') that are not mentioned in the description introduces ambiguity about the actual scope of the tool, making the purpose less crisp than it could be.

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 sibling list includes tools like 'fetch-status' and 'web-fetch', but the description does not differentiate normalize-url from these or explain under what conditions it should be preferred. This leaves the agent to infer usage context from the name alone.

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