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

Goes well beyond the annotations: discloses that no credits are spent, the board is unchanged, the failure mode for ineligible scenes is a descriptive refusal, and readiness is checked via get_generation. The 'changes nothing on the board' claim sits in tension with destructiveHint=true, but it accurately clarifies that the only side effect is a new clip generation, which is genuinely useful context for an agent.

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 purpose and downstream usage are front-loaded in the first sentence, with eligibility and side-effect facts following. Dense but every sentence carries distinct information; minor redundancy in 'the refusal says so'.

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?

For a two-parameter tool with an output schema, the description covers the key facts an agent needs: eligibility, no-cost/no-board-change behavior, refusal mode, and downstream consumption. It is essentially complete except for parameter meaning.

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 0% and neither parameter is explained: `storyboard_id` (uuid) and `scene` (integer >0) get no definition in the description. It is left ambiguous whether `scene` is an index, ordinal, or identifier, and no format guidance is given, so the description fails to compensate for the schema gap.

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?

States a specific verb and resource: 'Cut the stretch of source video a scene was read from', and names the downstream use (a clip model fed to animate_scenes). This distinguishes it from generate_clip/animate_scenes by scope, so an agent can identify it without opening the schema.

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?

Clearly gives the eligibility condition: only scenes born from an analysed video have a source, others are refused with an explanatory error. It also tells the caller what to do with the result (pass as `reference_videos` on animate_scenes). No explicit 'use X instead' routing to a sibling, but the when-to-use context is well established.

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