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

No annotations exist, so the description carries the full disclosure burden, but it only reveals a 'parse' verb with no mention of side effects, network access, return format, or the discard behavior repeatedly described in the schema ('discarded after the check'). The description's extraction framing ('parse owner and repo') also sits uneasily with the schema's validation-and-discard framing, leaving an agent unable to predict whether the tool returns a parsed object or a shape-check verdict. There is no annotation contradiction because no annotations were provided.

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?

A single, front-loaded sentence with zero filler words; the verb, resource, and outcome all appear within the first six words. Every element earns its place, and nothing could be trimmed without losing information.

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 nine parameters, no annotations, and no output schema, so the description must carry substantial explanatory weight, but it covers at most one parameter's use case. It neither explains what the tool returns (critical given the missing output schema), nor reconciles the eight unrelated parameters with the GitHub-repo purpose, nor clarifies when siblings like validate-json, weather-hint, or iana-zones should be chosen over this tool. The description would be adequate for a hypothetical single-parameter tool, not the one defined by this schema.

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 description coverage is 100%, establishing a baseline of 3, but the description actively adds a conflicting interpretation: it implies 'url' is a GitHub URL to extract owner/repo from, while the schema describes 'url' as an 'HTTPS URL to normalize or cite.' Eight of nine parameters (city, feed, zone, json, query, path, ref, host) have no connection to the description's stated purpose, and the description does nothing to help an agent understand which parameters are relevant or how they interrelate.

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 ('Parse') with a clearly identifiable resource ('a GitHub URL') and the expected extraction result ('owner and repo'), so an agent understands what the tool does. It does not explicitly differentiate from sibling shape tools (figma-url-shape, jira-key-shape, domain-shape) or normalize-url, and its narrow scope sits oddly against a schema covering nine unrelated input domains, but the stated purpose is unambiguous.

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 description gives no guidance on when to use this tool versus the many siblings that could plausibly handle GitHub URLs — normalize-url, domain-shape, browser-url-ok, playwright-url-ok — or versus the rest of the shape-tool family. No exclusions, conditions, or alternative routing are provided; the only usage context is what is trivially implied by the phrase 'parse owner and repo from a GitHub URL.'

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