topai_agentvision_crop

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description's trailing 'Stateless, read-only, idempotent' largely restates them. Where it adds real value is the payoff context ('reduce multimodal vision token consumption by up to 75%') and clarifying that the output is an ROI bounding box rather than a transformed image, though it omits the actual coordinate/format of the returned boxes.

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?

Three tight sentences, front-loaded with the computation and its benefit before the usage constraint. The final 'Stateless, read-only, idempotent visual ROI analysis' clause is mild redundancy against the annotations rather than new information, so it is slightly less than optimal.

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 two-parameter, single-required-input tool with no output schema, the description covers purpose, usage, cost benefit, and safety profile adequately. It could say more about what the returned ROI data looks like (coordinates, count, single vs. multiple boxes), which is the one gap an agent might care about.

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 both parameters are already documented, including the enum values and the 'auto' default. The description names the same element categories but adds no syntax, format, or defaulting nuance beyond the schema, so it sits at the baseline.

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 gives a specific verb and resource ('Computes optimal Region-of-Interest bounding boxes') plus the target element categories, and explicitly differentiates itself from the adjacent screenshotting tool. An agent can select it over `topai_headless_screenshot` without opening either schema.

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?

It states the positive trigger ('Use when preparing screenshots or document images for vision-capable LLMs'), the exclusion ('Do not use for taking the initial webpage screenshot'), and names the alternative (`topai_headless_screenshot` first). This is the full when/when-not/alternative triad.

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