verify_design_quality

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered by structured data. The description adds genuinely useful non-schema context: it returns a 0-100 score plus issues, and it requires local Python + Pillow, an environmental prerequisite an agent could not infer otherwise. It stops short of stating runtime cost or failure modes.

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 core is a single front-loaded sentence followed by a useful return/prerequisite note, which is efficient. However, the stray '[#8e74ec]' hex-color fragment at the end is unexplained noise that adds no value.

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 4-parameter read-only tool with no output schema, the description does well to state the return shape (score + issues) and the local-runtime requirement. It is incomplete on parameter usage and on how the optional image_url/workspace interact with design_uuid, leaving gaps an agent must guess at.

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 only 25% (four parameters, only needs_transparency documented), so the description must compensate and it does not — image_url, workspace, and design_uuid are never explained or given format/semantics. The 'Needs local Python + Pillow' note describes the environment, not any parameter.

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 ('Local QC gate for a design') and enumerates exactly what is checked: transparency correctness (alpha, clean corners, white premultiply), resolution, and detected text. This clearly separates it from siblings like verify_design_text, verify_mockup_quality, and check_design_compliance, which target narrower or different checks.

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?

Usage is only implied by 'QC gate' and the transparent-check scope. It never says when to prefer this over verify_design_text, verify_mockup_quality, or check_design_compliance, nor what preconditions (e.g. an already-uploaded design) must hold.

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