capture_views

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

No annotations provided, so the description carries full burden. It discloses privacy risks (images may contain confidential data, sent to client/host), cadence advice, behavior of parameters (with_dims is a no-op, section creates cut planes), return format (list of images + summary), and caveats (requires open part, temp files not deleted). No contradictions.

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 lengthy but well-structured with clear sections (privacy warning, cadence, args, returns, caveat, example). Each part adds value, though it could be slightly tightened. The front-loading of purpose and privacy warning is effective.

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 no output schema, the description covers return values (list of images + summary dict with resolved views, paths, with_dims, privacy note) and handles edge cases (unknown view raises ValueError, section behavior, with_dims no-op). Includes an example showing integration with other tools. All essential context for correct use is present.

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 has 0% description coverage; the description fully explains all three parameters. views: acceptable subset of view names, default, error on unknown. section: optional dict with plane and offset_mm, how it works for internal cuts. with_dims: accepted but no-op, rationale. Provides concrete examples and constraints.

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 clearly states the tool renders the active part or assembly to PNG for visual verification. It uses specific verbs and resources (render, PNG, visual verification) and distinguishes itself from sibling tools by emphasizing its role in visual checks, not modeling or other operations.

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 provides explicit guidance: use at checkpoints and end of build, not after every feature; trust cheaper signals in between; per-feature renders only for debugging; mandatory final render. It also mentions an alternative (verify_build_report capture_view_names) for bundling renders.

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