Find the most relevant document chunks with sources and per-stage scores using hybrid, dense, or BM25 retrieval. Empty results signal the query isn't covered by your documents.
Search a collection and return the most relevant chunks, each with its source and per-stage scores. mode: hybrid (default) | dense | bm25. Empty result = not in the docs.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | hybrid | |
| topK | No | ||
| query | Yes | ||
| collection | No | default |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It does reveal return shape ('each with its source and per-stage scores') and the important empty-result semantics. However, it does not explicitly state that this is read-only, what error conditions exist, or any rate-limit/auth considerations, leaving some behavioral traits implicit.
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?
Two sentences with no filler: purpose and output are front-loaded, mode options are compactly summarized, and the empty-result note earns its place as an operational signal. Highly efficient.
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?
The description covers purpose, output, mode options, and empty-result interpretation, which is adequate for a basic call with defaults. Yet with no annotations and no output schema, it leaves the meaning of 'collection' and 'topK' implicit, and it does not mention error behavior or side effects. Serviceable but not fully complete.
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 0%, so the description must compensate, but it only restates the 'mode' enum and default already present in the schema. It does not explain the semantics of 'query', 'collection', or 'topK' beyond what an agent might infer from names and defaults. This is a real gap for a tool with four parameters.
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 ('Search'), a resource ('a collection'), and a concrete output ('the most relevant chunks, each with its source and per-stage scores'). This clearly distinguishes it from sibling tools like answer, ingest_documents, list_collections, and evaluate_retrieval.
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 implies the primary use case: retrieving relevant chunks from a collection. It does not explicitly name alternatives or state when not to use it, but the context is clear enough that an agent should know to call this for raw retrieval rather than generation or ingestion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.