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

There are no annotations, so the description carries the full burden of behavioral disclosure. It only says 'parse', which implies a read-only computation, but it never states whether the tool makes network calls, how invalid or non-GitHub URLs are handled, what the exact return shape is, or that unrelated parameters are discarded. With no output schema, an agent has little information about what to expect.

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 one tight, front-loaded sentence with no redundant wording. It is efficient, but it is also too terse for a tool whose schema carries seven optional parameters and no annotations, so brevity comes at the cost of missing contextual 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?

With no annotations, no output schema, and a seven-parameter schema, a single sentence is not enough for an agent to invoke the tool confidently. The description omits how to supply the required input, what happens with invalid URLs, what the return representation is, and why most schema fields appear unrelated to the stated purpose.

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?

All parameters already have descriptions in the schema, which sets the baseline at 3. The tool description adds meaning by clarifying that the `url` parameter is specifically a GitHub URL from which `owner` and `repo` are parsed, going beyond the schema's generic 'HTTPS URL to normalize or cite'. It does not explain why city, feed, json, and path are present, so it cannot reach a 5.

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 names a specific verb ('parse'), a resource ('GitHub URL'), and a concrete outcome ('owner and repo'), which distinguishes it from sibling shape tools like figma-url-shape and jira-key-shape. It loses the top score because the input schema exposes many unrelated fields (city, feed, json, path) that are never reconciled with the stated GitHub-URL-only scope.

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 phrase 'from a GitHub URL' gives a clear but implicit usage signal: this tool is for extracting owner and repo from a GitHub link. However, the description does not explicitly state when to use it over other shape tools, nor does it mention exclusions or alternatives. It is enough for basic selection but not well-grounded guidance.

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