lookdev.compare

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

The description adds genuinely useful behavior beyond the annotations: candidates are applied transiently and rolled back before returning evidence, which explains why readOnlyHint=false yet destructiveHint=false and idempotentHint=true all hold simultaneously. This is meaningful context, and it does not contradict any annotation.

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 20-word sentence that front-loads the core action and packs baseline, candidate count, scope, and side-effect behavior with no filler. Every clause earns its place.

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 tool with a huge discriminated-union schema, three required parameters, and no output schema, one sentence is insufficient: what 'evidence' is returned (captured images? data?) is never stated, 'absolute candidates' is never defined, and the prior-inspection prerequisite is only implied. The agent is left to reverse-engineer the full comparison workflow from the schema alone.

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?

With 0% schema description coverage, the description must compensate, but it barely does: it hints that candidates number 1–3 (matching minItems/maxItems) and are 'absolute', yet it says nothing about how to construct the heavily constrained target union (six variants discriminated by type, each requiring expected_identity fields) or the capture settings. The most complex parameter, target, is covered only by the vague phrase 'one inspected LookDev property'.

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 description names a specific operation — capturing a baseline plus one to three candidates for a LookDev property — and the rollback clause distinguishes it from persistent mutation tools like object.set or material.set_input. However, 'absolute candidates' is unexplained jargon, and no sibling is named, so the differentiation is implicit rather than explicit.

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 wording 'for one inspected LookDev property' implies a prerequisite (prior inspection) and the rollback behavior implies this is for evaluating alternatives rather than committing values. But no explicit when-to-use/when-not-to-use guidance or alternative tool is named; an agent must infer the decision boundary between this and the persistent setters in the sibling list.

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