capture_view

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

With no annotations present, the description carries the burden and does real work: it discloses token cost per image, that sketches/work features are hidden by default and "restored after", and that isolate hides other components only "for the picture" — i.e. these are temporary view-state changes, not persistent edits. It does not say whether the document is left modified or whether the view orientation is restored.

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?

Purpose and the return type are front-loaded in the first line, the use-case follows, then args — no wasted sentences. The failure-mode examples (wrong-side flange, floating part) look decorative but directly explain why images beat numbers, so they earn their space.

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 9-parameter, no-annotation, no-output-schema tool, this is nearly complete: every parameter except `instance` is explained, cost and temporary-state behavior are disclosed, and the return type (images) is stated. The one real gap is that it does not say how multiple requested views map to returned images (count/order), which matters when batching iso,front,top.

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 coverage is only 11% (just `instance`), so the description must compensate and does: it enumerates the valid `views` tokens with an example, explains `fit_to` vs `isolate` as zoom-to vs show-only with the inside-components behavior, clarifies `up` semantics (Y-up template default vs Z-up models, with the axis each named view faces), and gives unit/cost meaning for width/height. Only `instance` is uncovered, and the schema documents it.

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 specific verb and resource — renders pictures of the active document returned as viewable images — and frames it against numeric inspection ("which the numbers alone don't show"), which separates it from inspect_model/measure_distance/check_interference. An agent knows immediately what it gets back: images, not data.

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?

Gives concrete when-to-use cues (verify a flange orientation, a door swing, a part floating off the frame) and a cost warning ("keep them modest — each picture costs tokens"). It never names an alternative tool or states when not to call it, so it stops short of full routing guidance.

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