light.create

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false, so the description is not required to restate those. However, the description adds only 'Risk: standard; maturity: L3' and a generic policy note, which are not behavioral details about the operation itself. It does not disclose what happens on creation (e.g., whether it replaces an existing light, whether it requires an active scene, or what the output contains). With no contradiction, but minimal added behavioral context, a 2 is appropriate.

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 short and front-loaded with the command name, but the two sentences are mostly boilerplate ('Risk: standard; maturity: L3', 'Per-request argument checks and session policy still apply') that do not earn their place for an agent trying to invoke the tool. It is not verbose, but it is under-specified rather than efficiently informative.

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?

The tool has 10 parameters, an output schema, and no nested objects, but the description provides almost no operational context. It does not explain what a light creation entails, what the output schema represents, or how this relates to the transaction/session flow implied by _transactionId and sibling transaction tools. For a creation tool with this parameter count, the description is incomplete.

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 50%, and the description adds no parameter-level meaning beyond what the schema provides. The schema itself documents color and location as 'Three finite numbers; rotation uses radians', which is helpful, but the description does not clarify the remaining parameters (name, size, type, energy, _requestId, _authorization, _expectedSceneRevision). Since coverage is at the 50% threshold, the baseline of 3 applies; the description neither compensates for the gap nor adds value.

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 identifies the tool as a PartMe Blender Harness command `light.create`, which implies creating a light, but it never explicitly states what the tool does (e.g., 'Creates a light object in the Blender scene'). The name and title carry most of the meaning; the description adds only harness context, not a clear verb+resource statement. It is distinguishable from siblings like blender_light_set_world_color by name, but the description itself does not differentiate it.

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 mentions that per-request argument checks and session policy apply, which is a generic constraint, but it gives no guidance on when to use this tool versus alternatives (e.g., blender_light_set_world_color, blender_object_create_mesh). There is no stated context, prerequisite, or exclusion. An agent cannot tell from the description when light.create is the right choice.

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