semantic_search

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

With no annotations, the description carries full responsibility for behavioral disclosure. It transparently explains scoring (blended BM25+vector), the explain flag, retrieval_mode field, fallback to BM25-only, validation against current source, and the distilled_records behavior with caps and labels. This is unusually thorough and exceeds typical expectations.

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 a single dense paragraph but packs numerous details without fluff. It is not excessively long for the information conveyed, though it could benefit from structured sections (e.g., bullet points) for readability. The front-loaded purpose sentence is clear, and every clause contributes meaningful behavioral or output context.

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 complexity (7 parameters, no output schema, no annotations), the description covers the most important behavioral aspects (scoring, retrieval_mode, fallback, validation) and relies on the schema for worktree and include. However, parameters like limit, graph_limit, and include_graph remain unexplained, and the description does not describe default behaviors for these. Overall, it is largely complete but misses some parameter context.

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 only 29%, so the description must compensate for undocumented parameters. It explains the 'explain' parameter explicitly and touches on 'include' indirectly (via fallback), but leaves limit, worktree, graph_limit, and include_graph unexplained. The output semantics (score, retrieval_mode) are covered, but input semantics beyond explain are not addressed, leaving a significant gap.

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: 'Search indexed source and docs.' This is a specific verb plus resource, and it distinguishes from other search tools like memory_search or rationale_search by focusing on source code and documentation. It also adds detail about scoring and retrieval modes, making the purpose 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 does not explicitly indicate when to use this tool versus alternatives. It describes behavior (scoring, fallback) but offers no guidance on when semantic_search is preferred over sibling tools like commit_search or memory_search. There is no mention of when not to use it or which alternative to pick.

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