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

Adds real context beyond readOnlyHint=true: the call is free, item ids are stable per scan_id, labels disambiguate repeats ("person (left)"), and an unscanned target returns 404. These are behavioral facts an agent cannot get from the annotations or schema. Return format is described at a high level only, but that is sufficient for a read tool.

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?

Dense and front-loaded: the payload is described first, then usage, then id behavior, then the error case. Every clause carries information, though the parenthetical details make it slightly longer than strictly necessary.

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 must carry the return-value burden, and it does: it enumerates the fields returned, the 0-1000 normalization, the scene narrative, and the id/label structure. Prerequisites and the 404 case are also covered, so an agent has everything needed to call and interpret it.

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 target_id and target_type are already documented by the schema and the enum is self-describing. The description's mentions of scan_id refer mainly to output item ids rather than input parameter semantics, so it adds little beyond 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?

States a specific verb+resource (get the detection engine's view of an image) and enumerates the exact payload: item names, categories, textures, colors, normalized bounding boxes, and a scene narrative. It is clearly distinguishable from siblings like scan_image (which produces the data) and cutout/get_cutout (which transform it).

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 explicit use cases ("see" an image's contents, or pick item names for restyle) and names the downstream alternative that consumes the output (restyle remove takes items [{id}]). It also states the prerequisite/fallback: 404 means never scanned, so run scan_image first.

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