search_code

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

Annotations already indicate readOnly and idempotent behavior. The description adds context about requiring a prior index call and that results include similarity scores. No contradictions with annotations.

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 very concise: three sentences plus a one-line prerequisite and an example. It is front-loaded with the core purpose, and every part is informative 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 no output schema, the description provides a high-level idea of return data (code chunks with similarity scores). It covers the essential prerequisite and gives an example. For a search tool with many filter options, a brief note on result ordering or pagination would improve completeness, but it is still adequate.

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 is 100%, so the schema already documents all parameters. The description only mentions fuzzy matching and filters in general terms, adding little meaning beyond the schema. The example demonstrates two required params but no extra semantics.

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 'Semantic search across the indexed codebase with optional fuzzy matching and filters' and specifies it returns 'relevant code chunks with similarity scores'. This distinguishes it from sibling tools like fuzzy_search which likely performs exact text search.

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?

It explicitly notes the prerequisite 'index_repository must be called first', which is helpful. However, it does not provide guidance on when to use this tool versus alternatives like fuzzy_search or query_codebase, nor does it mention when not to use it.

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