preview.capture

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful context: Risk: read, maturity: L3, and the export requirement for a committed snapshot. However, it does not explain output behavior (e.g., file format, return values) or why a committed snapshot is needed, leaving some ambiguity.

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 mostly direct, but the first sentence restates the tool name rather than adding content. The requirement list is efficiently worded, but the lack of purpose and parameter information means the limited space is not used to maximize value.

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?

Given 8 parameters, a complex harness context, and no parameter explanations, the description is far from complete. It explains eligibility (output root, policy, commit for export) but omits what the tool does, how to call it, and what outcome to expect. The existence of an output schema does not compensate for missing parameter and usage semantics.

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 8 parameters and only 38% schema description coverage, the description must compensate for undocumented parameters, but it omits any mention of width, height, snapshotId, milestone, or _expectedSceneRevision. It adds zero meaning beyond the schema; an agent cannot infer what these parameters refer to or what values are valid.

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 only names the command ('PartMe Blender Harness command `preview.capture`') and gives risk/maturity/requirements, but never states what the tool actually does (e.g., captures a preview image). An agent must infer the function from the name, and the description does not distinguish it from sibling tools like blender_view_present or blender_render_configure.

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 lists preconditions (approved output root, session policy, committed snapshot for exports) but provides no guidance on when to use this tool versus alternatives. There is no 'use when' or 'use instead' statement, leaving an agent to guess whether this belongs with preview workflows, export workflows, or other pipelines.

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