find_unused_css

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions that the tool 'Supports both URL analysis and local file analysis,' which adds useful context about input methods. However, it lacks details on behavioral traits like whether the analysis is read-only or has side effects, performance characteristics, or error handling. The 'SAVES: Claude context for strategic decisions' hint is vague and does not clarify operational behavior.

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 structured into sections (e.g., 'WORKFLOW:', 'TIP:', 'SAVES:'), which aids readability, but it includes vague or promotional phrases like 'Perfect for understanding complex code' and 'SAVES: Claude context for strategic decisions' that do not earn their place in a tool definition. The core purpose is front-loaded, but the additional sentences could be more focused on practical guidance.

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 complexity (13 parameters, no annotations, no output schema), the description is moderately complete. It covers the tool's purpose and basic usage context but lacks details on behavioral traits, output format, or error handling. The schema provides full parameter documentation, but without annotations or output schema, the description should do more to explain how the tool behaves and what results to expect.

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 100%, so the schema already documents all 13 parameters thoroughly. The description adds no specific parameter information beyond implying support for 'URL analysis and local file analysis,' which loosely relates to parameters like url, cssPath, and projectPath. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, as the description provides minimal additional semantic value.

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: 'Analyze CSS usage and identify unused selectors for performance optimization.' It specifies the verb ('analyze' and 'identify'), the resource ('CSS usage' and 'unused selectors'), and the goal ('performance optimization'). It also distinguishes from siblings by focusing specifically on CSS analysis, unlike broader tools like analyze_code_quality or analyze_project_structure.

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 clear context for when to use this tool: 'Perfect for understanding complex code, identifying issues, and technical debt assessment.' It also offers a workflow tip: 'Use Desktop Commander to read files, then pass content here for analysis.' However, it does not explicitly state when not to use it or name specific alternatives among siblings, such as find_unused_files or analyze_single_file, for different scenarios.

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