search_code

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

No annotations, description explains behavior: scans files directly, no index, returns highlighted snippets with file path and line. Adequate for understanding operation.

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?

Concise intro followed by clear bullet-like parameter explanations. No superfluous text. Well-structured and front-loaded.

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?

Covers all 4 parameters with defaults, output description. Missing potential performance notes or more complex examples, but sufficient given output schema exists.

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 0%, but description fully compensates: explains pattern with examples, path_glob with defaults and examples, context_lines range, max_results range. Adds substantial meaning.

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?

Clear verb 'search' and resource 'project files' with specifics (regex/substring, live, no index). Distinguishes from siblings like find_symbol and analyze_twig.

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?

Provides scenarios: 'finding usages, checking for patterns, searching non-PHP files.' Implicitly suggests one-off use due to 'no index' mention. Lacks explicit comparisons to siblings.

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