rastermoves_plan_refinement

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

It adds real behavior beyond annotations: no images are written, a retained background job is returned and must be polled, and base effect flags are "none" with conditional inference/download effects deferred to danceflow_component. That is useful, but describing the operation as effect-free while annotations set destructiveHint=true leaves the agent guessing about the actual destructive surface, and the state-mutating nature of spawning a retained job is not explained.

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?

Four short, front-loaded fragments with no filler; the key constraint (no image writes) leads. The telegraphic style ("Base effect flags: none") is terse to the point of being cryptic, but nothing is redundant.

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?

An output schema exists so return values need not be described, but for a tool with ~30 nested arguments, a permissions gate, and a destructive annotation, this four-line description is far too thin. It omits the relationship between permissions flags and the conditional effects it alludes to, which is the single most important thing an agent needs to call it safely.

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 description says nothing about the parameters — not the required input/output, not the refiner/tile/steps/guidance/strength knobs, and not the permissions object whose flags directly determine whether conditional effects fire. With a large nested arguments object and only 50% schema coverage, the description does not compensate for the undocumented parameters.

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?

"Print the validated canonical refinement plan" does convey this is a planning/dry-run tool rather than an image-writing one, which separates it from rastermoves_refine. But "validated canonical refinement plan" is jargon — the description never says what is being planned over (input/output/refiner settings) or what the plan contains, so the agent must infer purpose from the tool name and 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?

It implies a preview/plan step and gives explicit follow-up routing ("poll danceflow_job_status") plus a pointer to danceflow_component for conditional effects. However it never states when to choose this over rastermoves_refine or rastermoves_plan_all_models, and gives no prerequisites or exclusion conditions.

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