CrabCut

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

With no annotations provided, the description carries the full burden and adds valuable behavioral context: it discloses that the tool automatically handles export if needed, waits for readiness, and returns a download link. This covers key operational traits like async processing and output format. It doesn't mention permissions, rate limits, or error handling, but provides solid foundational behavior.

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 two concise sentences that are front-loaded with the core purpose and efficiently cover key behavioral aspects (export handling, waiting, return value). Every sentence adds value without redundancy, making it easy to scan and understand quickly.

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 no annotations and no output schema, the description does well by explaining the tool's behavior (export handling, waiting, returning a link) and purpose. It covers the essential context for a download tool with async processing. However, it lacks details on response format (e.g., URL structure) or error cases, leaving minor gaps in completeness.

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%, so the schema fully documents both parameters (clip_id and quality with enum values). The description doesn't add any parameter-specific details beyond what the schema provides, such as explaining clip_id format or quality implications. Baseline 3 is appropriate as the schema handles the heavy lifting.

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 clearly states the tool's purpose with specific verbs ('Get a download URL', 'Automatically handles export', 'waits until the clip is ready', 'returns the download link') and identifies the resource ('clip'). It distinguishes itself from sibling tools like 'get_clip' (likely retrieves metadata) by focusing on download URL generation with export handling.

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 implies usage when a download URL for a clip is needed, including automatic export handling if required. However, it doesn't explicitly state when to use this tool versus alternatives (e.g., 'get_clip' for metadata only) or mention prerequisites like clip existence. The guidance is functional but lacks explicit comparison or exclusions.

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