subject_box

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses the coordinate order [x,y,w,h] and the unit (document px), which is real information an agent needs to interpret the result, but it never states that this is a non-destructive read, whether it depends on AI services, or what happens on a layer with no detectable subject.

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?

A single tight sentence with the format and unit up front and no filler. It is arguably under-specified rather than padded, which is the better failure mode for conciseness.

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 annotations, no output schema, and 0% parameter description coverage, the description is the only source of structured information, and it leaves the 'project' parameter, layer identifier conventions, and tool prerequisites undocumented. For a two-parameter tool the scope is small, but the gaps are the ones an agent actually needs 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 0% for both parameters. The phrase 'of an image layer' loosely corresponds to the required 'layer' parameter, but the optional 'project' parameter is entirely unexplained, as is the accepted identifier format for either. The description does not compensate for the coverage gap.

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 names a specific resource and computation — the bounding box of the main subject of an image layer — so an agent knows it is a subject-detection read, not a crop or mask operation. It is clear but does not explicitly differentiate itself from siblings such as analyze_image, review_image, or set_mask, which also deal with image content and geometry.

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?

There is no when-to-use guidance at all: nothing says when this should be called instead of analyze_image or review_image, nor does it state prerequisites such as needing the layer selected or AI services enabled. The description only describes what the value is, not when to reach for it.

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