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

With no annotations provided, the description must carry the full burden of behavioral disclosure. It only states the parsing action without explaining what happens on invalid input, whether the URL is normalized, or if there are any side effects. The presence of nine parameters in the schema, only one of which (url) seems relevant, is not addressed. The description fails to disclose the tool's actual behavior beyond a minimal parse, leaving the agent uninformed about edge cases or response format.

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 a single, front-loaded sentence that directly states the core action without fluff. It is concise and easy to scan. However, it is under-specified, lacking any supporting details about parameters or behavior, which reduces its structural effectiveness. It earns a high score for conciseness but is limited by incomplete 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 description is severely incomplete for a tool with nine parameters and no output schema. It does not explain the role of most parameters, how the URL is extracted, or what the output looks like. An agent cannot confidently invoke this tool without additional inference. The lack of output schema and minimal description means the agent is left with substantial ambiguity about inputs, outputs, and error conditions.

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?

While schema coverage is 100% and each parameter has a description, the tool description adds no value in clarifying which parameters are relevant. It implies only the URL is used, but the schema includes unrelated fields like 'city', 'feed', and 'zone' with no explanation of their role. The description does not map parameters to its stated purpose, creating confusion about whether the tool accepts only a URL or uses all nine. This is a significant gap given the parameter ambiguity.

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 'Parse owner and repo from a GitHub URL' uses a specific verb (parse), a clear resource (owner and repo), and a precise source (GitHub URL). This distinguishes it from sibling URL-shape tools like figma-url-shape and jira-key-shape, which have different parsing targets. The purpose is immediately clear and 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 offers no guidance on when to use this tool versus alternatives. It does not mention conditions such as 'use this for GitHub URLs' or exclude cases like non-GitHub URLs. Siblings like figma-url-shape are not referenced, leaving the agent to infer usage from the tool name alone. No exclusions or when-not-to-use scenarios are provided.

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