Skip to main content
Glama

akb_search

Search documents with hybrid retrieval combining dense vector and BM25 keyword search via Reciprocal Rank Fusion. Handles natural language and keyword queries, returning URIs of relevant hits.

Instructions

Search documents with hybrid retrieval — dense vector (semantic) fused with BM25 sparse (keyword) via Reciprocal Rank Fusion. Handles both natural-language questions and short keyword queries well. For exact string / regex matches (code, URLs, version numbers) prefer akb_grep. Returns each hit's uri; use akb_drill_down or akb_get with that URI for full content. Response reports returned (in results) and total_matches (size of the deduped prefetch pool — NOT a corpus-wide hit count; vector ANN is top-K only). When truncated=true the prefetch pool was capped, meaning the corpus may hold more hits than reported — switch to akb_grep with count_only=true for an exact literal-substring count, or refine the query.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesNatural language search query
vaultNoLimit search to a specific vault
collectionNoLimit search to a specific collection
typeNoFilter by document type
tagsNoFilter by tags
limitNo
include_archivedNoInclude archived documents. Default false — `status: archived` docs are hidden from search.
source_urisNoRestrict the search to a specific set of already-known resources by their canonical akb:// URIs (e.g. from a previous akb_search / akb_browse). Hybrid retrieval (dense + BM25 + ranking) runs only inside this set, intersected with the other filters and your access. Omit for the normal whole-vault search.
Behavior5/5

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

With no annotations, the description fully bears the burden. It explains the hybrid retrieval method, the meaning of output fields 'returned', 'total_matches', and 'truncated', and the top-K limitation of vector ANN. It also clarifies default filtering for archived documents and the 'source_uris' parameter behavior.

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 a single, information-rich paragraph that is well-structured. It front-loads the purpose and method, then provides usage guidance, output explanation, and edge-case handling. No superfluous information.

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?

The description covers core functionality, all 8 parameters (with extra context for some), output field interpretations, limitations, and references to sibling tools. Despite no output schema or annotations, the agent can correctly invoke and interpret results.

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 88% (high), so baseline is 3. The description adds extra context: for 'query' it states it handles both natural language and keywords; for 'include_archived' it explains the default; for 'source_uris' it describes the hybrid retrieval within the set. This adds value 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 documents with hybrid retrieval (dense vector + BM25 via RRF). It explicitly distinguishes from sibling 'akb_grep' for exact matches, making the purpose unambiguous.

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

Usage Guidelines5/5

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

Provides explicit guidance: when to use (natural-language and keyword queries), when to prefer 'akb_grep' (exact string/regex), and advice on using 'akb_drill_down' or 'akb_get' for full content. Also explains when to switch to 'akb_grep' for exact hit counts when 'truncated=true'.

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/dnotitia/akb'

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