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

With no annotations, the description carries the full burden of disclosing behavior. It mentions that query and fragment are dropped, but the schema parameter descriptions indicate that many other inputs (ref, city, feed, json, path, zone, query) are also 'discarded after' some check, which the tool description completely omits. This creates a contradiction between the description and the schema, and the description fails to disclose that the tool likely performs multiple validation/discard operations beyond URL normalization.

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 (two sentences) and front-loaded with the primary function, but it is structurally inadequate because it ignores the majority of the tool's input surface. It omits essential information about the other parameters and the tool's actual multi-purpose nature. While brevity is good, it comes at the cost of completeness and accuracy.

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 annotations, and no output schema, the description is grossly insufficient. It only explains behavior for one parameter and leaves the rest unexplained. The schema descriptions hint at various validation/discard operations that the tool description does not cover. An agent cannot correctly invoke this tool for non-URL inputs or understand the full range of behavior, making the definition critically incomplete.

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?

Schema coverage is 100%, so baseline is 3. The description adds meaning for the 'url' parameter by specifying the output (origin, host, path) and the dropping of query/fragment, but it says nothing about the other 8 parameters. Since the description claims to be about URL normalization while the schema includes many unrelated parameters, it does not add value for those parameters and actually misleads the agent into thinking they are irrelevant. This fails to compensate for the fact that the schema descriptions of those parameters hint at additional behavior.

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 specific action ('Return origin, host, and path for a URL') but fails to acknowledge the tool's broader scope implied by the schema. The schema includes 9 parameters (ref, city, feed, json, path, zone, query) unrelated to URL normalization, each described as being 'discarded after' some check, suggesting the tool is actually a multi-purpose shape validator. The description misrepresents the tool's actual purpose and does not distinguish it from siblings like figma-url-shape or github-repo-shape beyond the URL focus.

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 any of the 27 sibling tools. The description does not mention alternatives, exclusions, or any conditions that would select this tool. An agent has no basis to decide between normalize-url and other URL/shape tools.

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