Analyze footage (vision)

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

Annotations indicate idempotentHint true, readOnlyHint false, destructiveHint false. The description adds behavioral details beyond annotations: it discloses caching behavior (skips already-analyzed clips unless force=true), cost estimation for runs needing >500 frames, and the requirement to confirm large runs. No contradiction with 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 concise, using two sentences to cover purpose, caching, and cost estimate. It front-loads the key action. However, a slight restructuring (e.g., separating the cost estimate note) could improve readability.

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 output schema, the description adequately describes the output (scored segments with subjects, camera movement, quality flags). It also covers the caching and cost estimation behaviors. It is complete enough for an agent to understand the tool's function and side effects.

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 coverage is 100% with descriptions for both parameters ('force' and 'confirm'). The description enriches meaning by linking 'force' to cache bypassing and 'confirm' to cost estimate approval, which goes beyond the schema's basic descriptions.

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: sampling keyframes and analyzing with Claude vision to build a footage graph with scored segments, subjects, camera movement, and quality flags. It also mentions caching and cost estimation behaviors, distinguishing it from sibling tools like skycut_scan_footage (which likely just scans) and skycut_search_moments (which searches already analyzed data).

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 explains when to use 'force' (to skip cache) and 'confirm' (to proceed after cost estimate for large runs). It does not explicitly contrast with alternatives like scanning, but the caching and cost estimate details provide clear context for when to invoke this tool.

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