viewport_capture

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

Annotations declare destructiveHint=true and readOnlyHint=false, so the agent knows this writes, but the description never explains why it is destructive — namely that an existing file at `path` may be overwritten (the schema exposes an `overwrite` flag defaulting to false). With annotations carrying the safety flag and no annotation contradiction, the description adds only the returned-path detail; it omits overwrite risk, blocking behavior, and cost of a "fresh" capture.

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. It is efficient, but its brevity is achieved by dropping information the agent actually needs rather than by tight editing.

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 destructive, 5-parameter write operation with no output schema and zero schema documentation, the description is far too thin: no parameter semantics, no overwrite behavior, no note on what the captured framing will be. Only the returned-path contract is covered.

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% across 5 parameters, and the description supplies no meaning for width, height, samples, or overwrite. Even `path` is ambiguous — "return its path" reads as an output rather than the required input destination — so the description fails to compensate for the coverage gap.

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?

"Capture a fresh workspace PNG and return its path" states a specific verb (capture) and resource (workspace PNG), plus the return value. It is clearly distinguishable from siblings like scene_info or viewport_mode_set, though it never clarifies what the viewport is framed on or whether this is a screenshot of the current view.

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 phrase "for image review" implies a purpose but gives no when-to-use guidance, no alternatives (e.g., camera_frame before capturing), and no prerequisites such as an active scene or viewport state. An agent must infer everything about when this call is appropriate.

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