Skip to main content
Glama

knowledge_search

Search a Markdown knowledge base with hybrid keyword and semantic retrieval, returning matching files, line ranges, and snippets so you can find answers before reading whole files.

Instructions

Гибридный поиск по базе знаний (ключевые слова + смысл). Возвращает файл, диапазон строк и фрагмент. Начинай с этого, а не с чтения файлов целиком.

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": "knowledge_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNohybrid
tierNo1 — только обзоры и память, 2 — только переписка
limitNo
queryYesпоисковый запрос
projectNoограничить проектом, напр. diffusion-app

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, the description carries the full burden: it helpfully discloses the return shape (file, line range, fragment), which compensates for having no output schema. It does not state read-only safety, result ordering/truncation behavior, index freshness, or what an empty result looks like — meaningful gaps for a search tool with zero annotation coverage.

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, front-loaded with what the tool does, then what it returns, then what to do — no filler and no redundancy.

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 five-parameter read-only search tool with no annotations and no output schema, the definition covers purpose, return shape, and entry-point policy adequately. The remaining gap is mode/tier semantics driving result quality, which an agent would have to infer.

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 60% (query, tier, project documented; mode, limit not). The description's "keywords + meaning" glosses the hybrid mode and implies chunk-level scoping, but it never explains the fts/vector alternatives, tier 1 vs 2, or how limit interacts with results. Baseline 3 given partial schema coverage and modest added meaning.

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 names a specific verb and resource (hybrid knowledge-base search combining keywords and meaning) and adds result granularity — file, line range, fragment. It also implicitly contrasts with reading whole files, so it is distinguishable from knowledge_read, though the sibling is not named explicitly.

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?

"Начинай с этого, а не с чтения файлов целиком" gives a clear default entry point plus one explicit exclusion (don't read entire files first). It stops short of saying when to prefer knowledge_read or project_context, and gives no guidance on choosing between modes.

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