ux_score

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

With no annotations provided, the description fully carries the transparency burden. It explicitly states 'Read-only analysis' and 'Does NOT require project_path - works on any feature list,' disclosing safety and scope constraints. It also details the return value structure (numeric score, mode, modules) and the absence of hidden side effects.

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 concise and well-structured. Each sentence contributes: purpose, input, return values, decision guidance, and a note on portability. It is front-loaded with 'OPTIONAL - call during Phase 2' and is free of fluff or repetition.

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?

Given the tool's simple one-parameter design and lack of output schema, the description is complete. It explains when to use it, what to pass, what it returns, and how to interpret the result within the pipeline (calling ux_generate or skipping). No additional information is needed for correct invocation.

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?

The schema already describes the sole parameter 'feature_list' at 100% coverage, so baseline is 3. The description adds meaningful context: 'Pass the feature list from the PRD' and 'works on any feature list,' which clarifies the origin and flexibility of the input. This extra semantic guidance justifies a 4.

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 clearly states the tool's purpose: 'call during Phase 2 (Define) to assess UX complexity.' It specifies the input (feature list) and output (numeric score, mode, modules), and distinguishes itself from sibling tools like ux_generate by explaining how results guide the next step. The verb 'assess' and resource 'UX complexity' are specific and unambiguous.

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 provides explicit when-to-use guidance: 'call during Phase 2 (Define)' and 'Pass the feature list from the PRD.' It also gives alternative handling: 'Use the result to decide whether to call ux_generate (for deep_dive/selective) or skip UX child PRD (for standard).' This directly addresses decision-making and differentiates from siblings.

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