Skip to main content
Glama

search_knowledge

Read-onlyIdempotent

Search a container using semantic, keyword, or hybrid mode to retrieve ranked passages with citations, scores, and document IDs. Refine the query and search again when results are thin.

Instructions

Search a container using semantic, keyword, or hybrid mode (Hybrid is the default and works well without tuning). Returns ranked passages with citations, scores, and document IDs. If the first query returns thin results, refine the query and call again.

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>",
      "containerId": "<containerId>"
    },
    "name": "search_knowledge"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoSearch mode: Semantic (vector), Keyword (full-text), or Hybrid (both). Default: Hybrid
pathNoOptional: Filter results to a folder subtree (e.g., '/docs/')
topKNoNumber of results to return. Default: 10
queryYesThe search query text
minScoreNoMinimum similarity score floor (0.0-1.0). Defaults to 0.05.
containerIdYesContainer or source ID or name to search within

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.4.0
    • changedInput schema / properties / containerId / description
      Previous value: -"Container ID or name to search within"New value: +"Container or source ID or name to search within"
  2. First observedv0.3.2

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds genuinely useful context beyond that: the shape of the response (ranked passages, citations, scores, document IDs) and the expected retry/refinement loop for weak results. It omits result limits or pagination behavior, keeping it below 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.

Conciseness4/5

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

Three short sentences, front-loaded with what the tool does, then return shape, then retry advice — no wasted wording. The clause about Hybrid being the default lightly duplicates the schema default, which keeps it from a perfect score.

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?

With no output schema, the description correctly steps in to describe the return payload, and it covers the mode decision and retry behavior for a six-parameter search tool. It leaves out result-limit or pagination expectations and any container-resolution nuance, but nothing essential for calling it correctly is missing.

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 every parameter including mode, path, topK, and minScore is already documented in the schema. The description only restates the mode options and the hybrid default, adding no syntax, format, or constraint detail beyond the structured fields. 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 gives a specific verb (search) plus the resource (a container) and enumerates the three retrieval modes, so the tool's function is unambiguous. It also states what comes back (ranked passages with citations, scores, document IDs). It does not name a sibling such as get_document or list_files to draw the boundary, so it falls short of a 5.

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

Usage Guidelines3/5

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

There is real guidance on mode choice ('Hybrid is the default and works well without tuning') and on iterating when results are thin. However, it never says when to prefer this over document-fetching siblings like get_document or get_documents, and offers no when-not conditions, so usage is only partially covered.

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