analyze_image

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 implies a read-only, non-mutating analysis operation (it returns numbers about existing state), which is a reasonable inference, and notes it can operate on a layer or box sub-region. But it doesn't state whether it requires an open project, whether the image must be loaded, or how results are returned. Adequate but incomplete for a zero-annotation 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?

A single dense sentence that front-loads the resource ('Numbers about the image') followed by the measurable outputs and a usage cue ('Measure before correcting'). No wasted words, though the opening phrase is a bit informal for a tool description.

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 three-parameter tool with 0% schema coverage and no annotations, the description leaves too much unspecified: what the 'project' parameter means, what format 'box' takes, whether the output is structured metrics or a report, and what 'layer' refers to (name, id, index). The output schema is absent, so the description should at minimum characterize return values, which it only partly does by listing metric names.

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 0% — none of the three parameters (box, layer, project) are described in the schema. The description mentions 'one layer, or a box' which hints at two of the three params but adds no format, type, or default information, and never mentions 'project' at all. With zero schema coverage, the description should compensate more thoroughly.

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 states a specific capability: returning measurements (brightness, contrast, clipped shadows/highlights, saturation, color cast, sharpness, dominant colors) about an image, layer, or box. It's distinct from sibling tools like describe_image (presumably descriptive text) and auto_enhance (which would apply corrections). However, it describes categories of output rather than naming the action cleanly — 'Numbers about the image' is informal.

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 closing phrase 'Measure before correcting' gives clear usage guidance — use this diagnostic tool prior to enhancement/correction operations like auto_enhance or match_color. It doesn't name those alternatives explicitly, but the sequencing guidance is actionable and distinguishes it from mutation tools among siblings.

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