production.qa_capture_viewport

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false), the description discloses two non-obvious traits: the capture is written to a *unique* file each time and temporary render settings are restored afterwards, meaning scene state is transiently changed but reverted. It omits where the file lands and any permission requirements, but the restore semantics are genuinely useful.

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 front-loaded sentence with no filler; the core action comes first and the side-effect clause follows. Slightly compressed—'unique local PNG' packs two ideas (uniqueness, filesystem location) that could each use a few more words.

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?

An output schema exists, so the returned PNG path and dimensions need not be spelled out. However, for a tool that mutates render settings and writes artifacts with two undocumented inputs, the description leaves an agent guessing about parameter meanings and file destination.

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 0% and the description mentions neither parameter. It is unclear whether 'max_size' is a pixel dimension, a file-size cap, or a scaling bound, and 'operation_id' (likely the async pattern used across these siblings) is unexplained. With two undocumented parameters, the description should compensate but does not.

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 ('Capture actual viewport') plus the output form ('unique local PNG'), which lets an agent distinguish it from render-oriented siblings like qa_render_preview or qa_render_multiview. It stops short of naming those alternatives explicitly.

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 never says when to choose this over the sibling capture/render tools (qa_render_preview, qa_render_multiview, character_capture_reference_views), nor does it state any prerequisites or conditions. Usage must be fully inferred from the tool name.

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