Scan footage

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

The annotations provide idempotentHint and destructiveHint. The description adds valuable behavioral details: idempotent behavior (skipping existing clips/proxies on re-run), non-modification of source, and the specific outputs (database, manifest, proxies). This goes beyond annotations.

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 sentences, front-loaded with the main action and file types, then details on idempotency and safety. No wasted words.

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 explains what the tool does, its inputs (active project's source path), outputs (database, manifest, proxies), and behavioral traits. It lacks explicit mention of return value or error cases, but given no output schema and simple nature, it is mostly complete.

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?

With zero parameters, schema coverage is 100%, and no additional parameter info is needed. The description adds no param details, but baseline is 4 per guidelines.

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: recursively index video files (specifying extensions), extract metadata using ffprobe, store in database and manifest, and build proxies. It is specific about the resource (active project's source path) and action (indexing and proxy creation), distinguishing it from sibling tools like skycut_analyze_footage which likely perform further analysis.

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 does not explicitly state when to use this tool versus alternatives like skycut_analyze_footage. It implies usage for initial footage ingestion but lacks guidance on prerequisites or ordering, which would help an agent decide.

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