cook_frame_range

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

With no annotations, the description fully carries behavioral disclosure: frames are cooked in order so solvers accumulate correctly, results come in one round trip, per-frame errors and aggregates are reported, and the frame is left at the end for screenshots. It also warns that skipping frames produces discontinuous time steps and invalid results.

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 front-loaded with the core operation, then gives usage rationale, and ends with a compact parameter walkthrough. Each sentence adds information—even the repeated 'one call vs. one per frame' point is used to reinforce the alternative comparison.

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 or annotations, the description covers the key invocation facts: what it does, when to use it, parameter semantics, side effects, and the shape of returned information (per-frame cook time, errors, counts, attribute aggregates, volume details). A precise JSON return layout is not specified, but the description provides enough for an agent to select and call the tool correctly.

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?

The schema provides types, defaults, and required status but no descriptions, so the Args section must and does compensate. It explains node_path as the measured output, start/end defaults to the playbar, step's solver-specific warning, the aggregate math for attribs, and exactly what volumes adds.

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 opening sentence states a specific verb ('cook'), a resource ('a node'), and the output ('report what changed on each frame'), which clearly distinguishes it from sibling tools like set_frame and get_cook_status. The usage note that this is how you advance a sequential solver further reinforces its unique role.

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 explicitly says to prefer this over set_frame in a loop or stepping by hand, and explains the advantage in a single call for a 100-frame check. It also gives a strong condition for when not to set step above 1.0 (any solver), making selection guidance actionable.

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