Batch-assign RGB colors to the active saved part or named top-level assembly components, with preflight checks, color readback, and a single redraw—no save or rebuild.
Batch RGB on the exact active saved part or named top-level assembly components. Preflights all targets, reads back colors, redraws once. No save or rebuild.
| Name | Required | Description | Default |
|---|---|---|---|
| dry_run | No | ||
| request_id | Yes | ||
| assignments | Yes | ||
| result_view | No | ||
| document_path | Yes |
Changes observed during successful MCP inspections.
v0.7.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare destructiveHint=true and idempotentHint=false; on top of that the description discloses that it preflights all targets, reads colors back, and redraws once, which tells the agent this behaves atomically with a single visual refresh. "No save or rebuild" is valuable context that the change is in-memory and not persisted. It omits undo/reversibility and the meaning of dry_run, so not a 5.
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?
Three short sentences with zero filler and the target scope front-loaded ahead of the behavioral guarantees. However, the terseness tips into ambiguity – "Batch RGB" and "Preflights all targets" cost clarity that one more clause could have bought.
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 destructive, non-idempotent mutation with 5 parameters, 0% schema description coverage and no output schema, the description covers scope and the preflight/no-save guarantees but says nothing about dry_run, request_id, or what summary vs full returns. Enough to call it safely-ish, not enough to call it well.
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%, so the description carries the full burden, yet it only implicitly covers document_path and the component field of assignments. dry_run, request_id, and result_view (enum summary/full) get no explanation at all, and the exact shape of color_rgb is left entirely to the schema.
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?
"Batch RGB" states a specific verb and resource, and the tool is scoped precisely to "the exact active saved part or named top-level assembly components", which tells an agent exactly what object set it can touch. It stops short of naming a sibling (e.g. set_appearance) to contrast against, and the telegraphic phrasing ("Batch RGB on...") requires a second read to parse.
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?
Preconditions are implied rather than stated: the target must be the *active* and *saved* part, and assembly targets must be *top-level*, which quietly rules out unsaved or nested-component use. There is no explicit guidance on when to prefer this over set_appearance, nor any mention of when to use dry_run, leaving the agent to infer alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.