screenshot

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

Despite annotations declaring readOnlyHint=true and destructiveHint=false, the description adds substantial behavioral detail beyond them: token-cost dials (scale/format/quality), cropping behavior (clamped), and the annotate feature that returns a structured marks legend. It also warns about PNG-only for editor target, which is not in annotations.

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 dense but well-structured, front-loading the core purpose and then using semicolons and clauses to group related details. It is longer than two sentences, yet every clause earns its place by explaining token costs, target differences, and the annotate workflow, making it efficient for a tool with 8 parameters.

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 covers the return behavior: images are inline, and annotate also returns a marks legend. It addresses all eight parameters either in prose or via the schema, and clarifies key edge cases like clamping and PNG-only for editor. Enough detail for an agent to know when and how to invoke correctly.

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 100%, so the baseline is 3, but the description enriches several parameters: scale=0.5 quarters the pixels, jpeg/webp compress far below PNG, region is clamped, and annotate returns a structured legend. It does not mention max_marks in prose, but the schema already documents it, so the added value is enough to push to 4.

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 opens with 'Capture an image the agent can see,' which is a specific verb+resource statement. It clearly distinguishes between game and editor targets and separates itself from sibling tools like ui_snapshot by positioning itself for visual inspection rather than functional state.

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 explicitly names an alternative: 'For pure functional state, ui_snapshot is cheaper than any image.' It also provides guidance on when to use annotate=ui for both visual and interactive state, and differentiates game vs editor targets with concrete channel semantics (runtime vs viewport).

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