Skip to main content
Glama
Datris MCP Server

Datris MCP Server

search_chroma

Run semantic search across a Chroma collection using a natural language query to return similar document chunks and similarity scores for retrieval-augmented answers.

Instructions

Semantic search across a Chroma vector database collection. Takes a natural language query, generates an embedding, and returns the most similar document chunks with similarity scores. For RAG: pass the returned text to ai_answer with the user's question.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_chroma"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesNatural language search query
top_kNoNumber of results to return (default: 5)
collectionNoChroma collection name (default: documents)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full burden. It does disclose the internal behavior (embedding is generated from the query, results are ranked by similarity and include scores), which is more than a bare restatement, but it says nothing about failure modes, whether the collection must pre-exist, or any auth/permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the core action before the mechanics and the RAG tip. Minor redundancy in restating that the query is natural language, which the schema already says, but overall there is little waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter tool with no output schema and no annotations, the description covers the essentials: what it does, how results are produced, and roughly what is returned (chunks plus similarity scores). Gaps remain around error behavior and return shape details, but they are modest at this complexity level.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters (query, top_k with default 5, collection with default documents) are already documented in the schema. The description restates that the query is natural language but adds no extra semantics such as query length limits or what a larger top_k costs. Baseline 3 applies when the schema does the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource — semantic search against a Chroma vector collection — and describes the mechanism (embedding generation) plus what comes back (similar document chunks with similarity scores). Naming Chroma explicitly separates it from the sibling vector-store tools search_milvus, search_pgvector, search_qdrant, and search_weaviate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a concrete usage context: for RAG, feed the returned text into ai_answer along with the user's question, which effectively routes the agent to the correct follow-up sibling. It stops short of any exclusions — nothing says when to use a different vector store or what to do if the collection does not exist.

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

Deploy Server

Other Tools