design_review

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

With no annotations, the description takes on full responsibility for behavioral disclosure. It openly states this is a heuristic, not a human designer, explains it reasons only about color statistics and not glyphs, and advises visual confirmation for hero-value hierarchy. It also discloses the need for the pebble CLI in emulator mode and describes the output as a JSON critique plus image.

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?

The description is well-structured and front-loaded with the primary purpose. It uses separate paragraphs for parameters, limitations, and return values without fluff. Every sentence contributes to the agent's ability to invoke the tool correctly, making the length justified.

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?

The description covers input types, parameter semantics, return value contents, and limitations, which is strong given no annotations and no output schema. It does not detail the exact JSON structure or error behavior, but for selection and invocation purposes it is sufficiently complete to guide an agent.

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%, but the description fully explains both parameters. It details the accepted formats for `source` (filesystem path, base64, data URI, or 'emulator') and the meaning of `regions` (N×N contrast grid, default 3), adding crucial context beyond the bare schema.

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 opens with a specific verb+resource phrase: 'Critique a Pebble screenshot against the design system.' It clearly states the tool's function and differentiates it from siblings like color_nearest or image_quantize by focusing on holistic design system compliance.

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 description gives clear context for when to use the tool (analyzing screenshots for design adherence) and even includes a cross-reference to capabilities() for emulator capture requirements. However, it does not explicitly mention when not to use it or name alternative tools for simpler tasks, so it lacks full exclusion guidance.

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