production.udim_plan

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), yet the description still adds real value: it discloses that incomplete, ambiguous, and cross-island assignments are rejected, and that apply=false keeps the operation non-mutating. It does not explain plan output or how to feed the plan downstream, but the core behavioral contract is stated.

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?

A single dense sentence that front-loads the action and appends the rejection and apply=false constraints without filler. It is compressed to the point of near-opacity for readers unfamiliar with the UDIM domain's jargon, but no sentence is wasted.

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-value detail is not required, but with two required parameters at 0% coverage and a freeform/nested options object, the description leaves too much undocumented—especially the unspecified 'relationship' parameter. The description also never explains what the resulting plan contains or how it is consumed by udim_apply_plan.

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 description coverage is 0% and one parameter is a freeform 'options' object with additionalProperties=true and nesting, so the description must carry the burden. It only vaguely gestures at option contents (material_index, faces, apply) and never mentions the required 'relationship' parameter at all, leaving an agent to guess key names and value shapes.

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 concrete verb+resource: 'Plan explicit semantic material_index or faces assignments to configurable UDIM1001+ tiles.' An agent can tell this produces an assignment plan for UDIM tiles rather than performing packing/UV generation. It never names the obvious sibling production.udim_apply_plan, so the differentiation is only implied via 'apply=false'.

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 'apply=false' clause implies this is a dry-run/planning stage that precedes production.udim_apply_plan, and the rejection rules hint at a validation gate before applying, but there is no explicit 'use this when X, use Y instead' statement. Usage must be inferred from context.

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