fusion_look

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered by structured data, lowering the burden on the description. The description adds the roster of valid named views, which is genuinely useful operating context, but it says nothing about what happens when views is null, whether captures are synchronous, or how results are delivered.

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?

One tightly packed sentence with the action front-loaded and the valid values listed inline. Every word earns its place, including the view list, which doubles as parameter documentation.

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?

With no output schema, the description should indicate what the caller receives — image bytes, base64, a file path, or a URL — and it is silent on this. For invocation itself it is adequate: view names are given and defaults for width/height come from the schema. The unresolved null-views behavior and return format are the notable gaps.

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%, so the description must carry parameter meaning. It does supply the critical semantic — the accepted view names — which the schema does not enumerate at all. But it leaves width and height entirely unexplained (units, whether they matter when a view is not specified) and doesn't say whether views=null means all views or the current view.

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 states a specific verb ("Screenshot") and resource ("the active Fusion viewport") and enumerates the seven valid viewpoints, so an agent knows exactly what it produces. It doesn't explicitly contrast with fusion_render or fusion_export, which likely also produce visual output, so sibling differentiation is inferred rather than stated.

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?

Usage is implied by the enumerated named views — the agent can infer this is for quick visual inspection at standard orientations. However, there is no statement of when to prefer this over fusion_render or fusion_export, nor any prerequisites (e.g., an open active document).

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