concept_search

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

No annotations provided, so the description fully carries the burden. It discloses that the search is fuzzy, mines local co-occurrence data, does not use embeddings, and sends no data externally. It also explains the flow parameter's effect. This is very transparent about the tool's behavior and privacy implications.

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 extremely concise, accomplishing its goal in two sentences. It front-loads the key purpose ('FUZZY search for a concept you can't name') and adds the key usage hint immediately. Every sentence adds value without redundancy.

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 has 4 parameters and no output schema or annotations, the description covers core functionality well but lacks details on projectPath and maxResults. The return format is only minimally described as 'ranked file:line'. For a complete understanding, an agent might need more context on these elements.

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 50%, with descriptions for q and flow. The description adds value by explaining q should use 'concrete nouns' and flow traces the call graph. However, projectPath and maxResults are left completely undescribed in both schema and description, meaning half the parameters lack semantic guidance.

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 it performs a fuzzy search for concepts when the user doesn't know the symbol name. It specifies the method (mining dictionary from identifier+comment co-occurrence) and output (ranked file:line). This distinguishes it from sibling tools like search_symbol and search_text, which are more exact or text-based.

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?

Explicitly states when to use: 'Use when you don't know the symbol name.' This implies alternatives (e.g., search_symbol) are more appropriate when the name is known. It also describes the flow parameter for call graph tracing. However, it doesn't explicitly list when not to use or mention other sibling tools.

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