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

With no annotations present, the description carries the full burden, and it does disclose a genuinely useful trait: the read-only normalization behavior and the fact that query and fragment are stripped. However, it fails to surface that the tool also accepts several unrelated params (city, json, ref, path, feed) that are validated and discarded, per the schema. The simple single-URL mental model the description creates partially conflicts with the multi-param reality of the tool.

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?

Exactly two sentences with zero filler: the core behavior is front-loaded and the exclusion detail ('Query and fragment are dropped') earns its place. This is appropriately sized for a simple behavioral contract.

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 7-parameter schema, no annotations, and no output schema, the description leaves out essential call context: which parameter is the primary input, whether it is required, what the return format looks like, and why a URL-normalization tool accepts city, JSON, git ref, and file-path inputs. The description is complete about output semantics but incomplete about how to construct a correct invocation.

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% — all seven parameters have individual descriptions — so the baseline of 3 applies. The description adds output semantics that map to the `url` parameter, but it never names which parameter is the one being normalized, and several params (url, feed, host, path) are URL-like, creating ambiguity. The description thus adds marginal meaning but does not compensate for the unclear relationship between the behavior and the parameter set.

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 verb ('Return') plus a well-defined resource ('origin, host, and path for a URL'), and even clarifies exclusions ('Query and fragment are dropped'). This distinguishes it from validation-oriented siblings like browser-url-ok and web-fetch in substance. It stops short of a 5 because it never explicitly contrasts itself with URL-shape siblings such as domain-shape or github-repo-shape.

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?

There is no guidance on when to use this tool versus alternatives, no exclusions, and no stated prerequisites. An agent is given zero help choosing between this and domain-shape, fetch-status, or figma-url-shape. The second sentence ('Query and fragment are dropped') is a behavioral constraint, not usage context.

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