Skip to main content
Glama
Datris MCP Server

Datris MCP Server

search_milvus

Searches a Milvus vector collection semantically by converting a natural-language query into an embedding and returning similar document chunks with similarity scores for RAG answer generation.

Instructions

Semantic search across a Milvus 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_milvus"
  }
}

Input Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full disclosure burden. It usefully reveals the internal pipeline (embedding is generated for you) and the return shape (most similar document chunks with similarity scores), which goes beyond a bare 'search' label. It says nothing about failure modes: what happens if the named collection does not exist, whether any credentials/index state are required, or any limit on top_k.

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

Conciseness5/5

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

Three short sentences: what it does, what it returns mechanically, and how to chain the output. The purpose is front-loaded and no sentence is redundant or padded.

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 3-parameter read tool with no annotations and no output schema, the description covers the essentials: input nature, the embedding step, the ranked-chunk return, and downstream usage. Only operational edge cases (missing collection, top_k bounds, empty results) are absent, which is a modest gap rather than a blocking one.

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 coverage is 100%, so query, top_k (default 5) and collection (default documents) are all already documented in the schema. The description adds no syntax, range, or format guidance beyond that; its only parameter-adjacent contribution is that the query is natural language, which the schema already states. Baseline 3 applies.

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

Purpose4/5

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

The description pairs a specific verb with a specific resource: 'Semantic search across a Milvus vector database collection', and explains the mechanism (embedding generation, ranked chunks with scores). It implicitly distinguishes itself from the backend-specific siblings (search_chroma, search_pgvector, search_qdrant, search_weaviate) by naming Milvus, but never explicitly says 'use this for Milvus collections, use X for other backends'.

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?

It gives a concrete usage scenario: 'For RAG: pass the returned text to ai_answer with the user's question', which tells the agent both when to call it and what to do with the result. There are no negative cases or exclusions (e.g., when to prefer a keyword search or another backend's search tool), so it stops short of a full when/when-not statement.

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