Skip to main content
Glama
dipseth

google-workspace-unlimited

Qdrant Vector Search Tool

qdrant_search
Read-onlyIdempotent

Search a Qdrant vector database using natural language, filters, or DSL queries. Retrieve semantically similar results with relevance scores.

Instructions

Search through Qdrant vector database using natural language queries, filters, point IDs, or DSL filter notation. Supports semantic search, service-specific filtering, analytics queries, recommendation-style example search, direct point lookup, and advanced DSL queries. When filter_dsl is provided, routes to the DSL executor for precise filter-based search. Returns structured search results with relevance scores and metadata.

Parameterized DSL Grammar: symbol{param1=value1, param2=value2}

Values can be:

  • Strings: "hello"

  • Numbers: 42, 3.14

  • Booleans: true, false

  • Null: null

  • Nested symbols: symbol{...}

  • Lists: [item1, item2, ...]

Key filter symbols (used in 'dsl' param): D_5 = DatetimeRange ʄ = FieldCondition ƒ = Filter F_6 = FilterSelector ℏ = HasIdCondition I_2 = IsEmptyCondition I_0 = IsNullCondition ɱ = MatchAny ṁ = MatchText M_0 = MatchTextAny ☆ = MatchValue ř = Range

Advanced query symbols (used in 'query_dsl'/'prefetch_dsl' params): (Types without Unicode symbols use full class names as identifiers) Å = AcornSearchParams C_14 = ContextExamplePair ¢ = ContextPair C_0 = ContextQuery D_6 = DiscoverInput D_2 = DiscoverQuery D_4 = DiscoverRequest D_21 = DiscoverRequestBatch ℱ = Fusion φ = FusionQuery ø = OrderBy ɵ = OrderByQuery ¶ = Prefetch ʔ = QuantizationSearchParams R_12 = RecommendGroupsRequest R_2 = RecommendInput R_4 = RecommendQuery R_5 = RecommendRequest R_18 = RecommendRequestBatch R_10 = RecommendStrategy ♦ = SearchParams

Examples: ƒ{must=[ʄ{key="tool_name", match=☆{value="search"}}]} (filter by tool_name), ƒ{must=[ʄ{key="tool_name", match=ɱ{any=["send_dynamic_card", "send_gmail_message"]}}]} (match any of multiple values).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of results to return (1-100)
queryYesSearch query string (natural language, filters, or semantic text for DSL mode)
dry_runNoIf True with filter_dsl, parse+build without executing
query_dslNoOptional advanced query DSL (RecommendQuery, FusionQuery, OrderByQuery)
collectionNoOptional Qdrant collection name to search. If not provided, uses the server's default collection.
filter_dslNoOptional DSL filter string (e.g., 'ƒ{must=[...]}')
prefetch_dslNoOptional multi-stage Prefetch DSL
score_thresholdNoMinimum similarity score (0.0-1.0)
user_google_emailNoUse 'me' or 'myself' for auto-resolution to authenticated user, or provide specific email address. If None, uses current authenticated user (auto-injected by middleware).
negative_point_idsNoOptional list of point IDs to use as negative examples
positive_point_idsNoOptional list of point IDs to use as positive examples

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNoError message if search failed
queryYesThe search query used
resultsYesSearch results
dsl_inputNoDSL filter string when using DSL search mode
query_typeYesType of query (semantic, service_history, dsl, etc.)
search_vectorNoNamed vector used for search (e.g., 'components', 'inputs', 'relationships')
total_resultsYesNumber of results found
collection_nameYesQdrant collection name
built_filter_reprNoDebug repr of built filter object
processing_time_msYesTime taken to process the search
Behavior5/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false. The description adds substantial behavioral context: it explains routing logic for filter_dsl, details the DSL grammar (including symbols and value types), and notes that results include relevance scores and metadata. No contradictions; description enriches transparency.

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?

The description is well-structured: main purpose first, then DSL grammar details and examples. Every section adds necessary information for a complex tool. Despite length, it is efficient and front-loaded with the core functionality.

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

Completeness5/5

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

Given the tool's complexity (11 parameters, advanced DSL), the description covers all search modes and parameter roles. It mentions return type (structured results with relevance scores and metadata). Output schema exists, so no need for return value details. Complete for the tool's scope.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3. The description provides extensive additional meaning for DSL-related parameters (filter_dsl, query_dsl, prefetch_dsl) with full grammar specifications and examples. For other parameters like limit and score_threshold, it adds minimal beyond defaults. Overall, the description significantly enhances parameter understanding beyond the schema.

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?

The description clearly states the tool searches a Qdrant vector database using natural language, filters, point IDs, or DSL notation. It lists multiple search modes (semantic, analytics, recommendation, direct lookup) and distinguishes itself from sibling search tools by explicitly naming 'Qdrant vector database'.

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?

The description explains when to use filter_dsl (routes to DSL executor) and provides detailed DSL grammar and examples. It implies usage for Qdrant data but does not explicitly mention when not to use it or compare to sibling search tools for other data sources. Clear context but lacks exclusions.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dipseth/google_workspace_fastmcp2'

If you have feedback or need assistance with the MCP directory API, please join our Discord server