semantic_search

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

Annotations only declare readOnlyHint=true, so the description carries most of the burden and does add real context: the retrieval mechanism, the RRF fusion used by hybrid mode, and the hard dependency on prior indexing. It omits cost/latency considerations for large indexes or anything about how results are truncated, which keeps it from a 5.

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?

Four short, front-loaded blocks: what it does, what it returns, the mode option, and the prerequisite. No filler sentences and the most consequential routing information (indexing prerequisite) is stated plainly.

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?

An output schema exists, so the description is not obligated to detail return values, yet it still summarizes them. Combined with the stated prerequisite and mode guidance, an agent has enough to call this correctly; only edge behavior (empty index, scope of 'all indexed folders') is left implicit.

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 baseline is 3. The description's note about mode='hybrid' restates what the schema already says ('vector + full-text via RRF') rather than extending it, and top_k, file_type, and folder_path are left entirely to the schema.

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?

States a specific verb and resource ('search indexed documents using natural language') plus the mechanism (semantic similarity) and the return shape (ranked chunks with source paths and relevance scores). It names index_folder as the enabling prerequisite, which cleanly separates it from get_index_status and reindex_file.

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?

Gives explicit conditions for the key decision point: default vector mode vs mode='hybrid' when keyword + semantic matching is wanted, and it clearly states the folder must be indexed first with index_folder. It stops short of naming when-not-to-use or a competing sibling for the same job, so it is not a full 5.

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