mcp-llm-wiki

Search wiki

wiki_search

Read-only

Find relevant wiki pages using hybrid BM25 and semantic vector search, returning the best match per page with path, heading path, and excerpt.

Instructions

Hybrid search over the wiki: BM25 (SQLite FTS5) and local CPU vectors combined with Reciprocal Rank Fusion. Returns the best hit per page with path, heading path, line range, and a frontmatter excerpt. Use mode='bm25' for exact terms, mode='vector' for semantic paraphrases, otherwise 'hybrid'.

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": "wiki_search"
  }
}

Input Schema

Name	Required	Description
`k`	No	Max hits (default 10).
`mode`	No	Search method (default: hybrid).
`tags`	No	Only pages carrying all of these tags.
`type`	No	Restrict to a frontmatter type.
`layer`	No	Layer: 'wiki' (default) or 'raw' (sources).
`query`	Yes	Natural-language or keyword query.
`folder`	No	Restrict to this folder, relative to the wiki root.
`status`	No	Restrict to a frontmatter status.
`recursive`	No	Include subfolders of `folder` (default true).
`pathPrefix`	No	Restrict to paths starting with this prefix.
`includeText`	No	Include full chunk text instead of an excerpt.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.2Sep 5, 2026

TDQS

A4.6/5.0

Behavior5/5

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

The description goes well beyond the readOnlyHint annotation by disclosing the algorithm (SQLite FTS5 BM25 + local CPU vectors), the fusion method (RRF), the deduplication behavior ('best hit per page'), and the exact return fields. This is rich behavioral context with no contradiction against annotations.

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?

Two sentences deliver the core behavior, return format, and mode guidance with no filler. The most important scoping information is front-loaded, and every clause earns its place.

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 tool with 11 parameters and no output schema, the description covers the essential context: algorithm, result granularity, and return fields. The remaining parameters are fully documented in the schema, so their omission is acceptable. It could be slightly more explicit about result ordering or overall response shape, but k and the stated return fields carry most of that burden.

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 description coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining what the mode enum actually does: bm25 for exact term matching, vector for semantic paraphrases, and hybrid as the default fallback. It does not need to restate schema-documented parameters.

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 names a specific verb (search), a resource (the wiki), and the concrete retrieval strategy: hybrid BM25 + vector search with Reciprocal Rank Fusion. It also states the per-page output shape, making the tool clearly distinguishable from siblings like wiki_list_pages or wiki_read_page.

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 gives actionable guidance: use mode='bm25' for exact terms, mode='vector' for semantic paraphrases, and hybrid otherwise. It does not explicitly contrast this tool with sibling alternatives, such as when to prefer wiki_list_pages instead, so it stops short of full alternative routing.

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

Deploy Server