Supervision Draw

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

With no annotations present, the description carries the full burden and does well: it discloses input caps (4 megapixels, 500 detections), label constraints (ASCII), the conditional requirement that polygon be supplied on every detection when mask/polygon/halo are used, the default annotator set, the return payload (base64 PNG/JPEG, size, counts per class), and the price. It does not mention auth, rate limits, or failure behavior, which keeps it out of the top band.

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?

Purpose is front-loaded and the two sentences are information-dense with no filler. The long parenthetical annotator enumeration is bulky but is the only place a caller sees the full vocabulary, so it earns its space.

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?

No output schema exists, and the description compensates by describing the return value (annotated image as base64 PNG/JPEG, plus size and per-class counts). Combined with the input limits, ordering constraint, and pricing, an agent has everything needed to call it 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 description coverage is 100%, so the baseline is 3. The description largely restates schema content (annotator type list, default [box, label], ordering rule) rather than adding new semantics, so it does not earn above 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?

States a specific verb and resource ('Annotate an image with detections') and enumerates the exact annotator vocabulary the tool understands, so an agent immediately knows the operation and its scope. There are no siblings, but the definition is self-distinguishing from any generic image tool.

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?

Gives a concrete ordering rule ('applied in order'; 'Put blur, pixelate, color, mask or background_overlay before box and label') that tells the agent how to construct a valid call. There are no sibling tools, so there is no alternative to route against, but no explicit when-not-to-use guidance is offered either.

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