Skip to main content
Glama

cachly — Explain it once. Every AI knows it.

brain_search

BM25+ full-text search over ALL brain data: lessons, context entries, session history, CKG nodes, roadmap items. Unlike smart_recall (which focuses on lessons + context), brain_search casts a wider net. Use when smart_recall returns nothing or when you want to find anything the brain knows about a topic.

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": "brain_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax results (default: 15)
queryYesWhat to search for
instance_idNoBrain instance ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden; it does disclose the retrieval algorithm (BM25), the corpus searched, and the fallback role, which implies a read-only lookup. It does not state result ordering/ranking behavior, pagination, or whether results are truncated by default beyond the schema's limit hint.

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?

Front-loaded with the core capability and corpus, followed by the differentiation and use condition. The second and third sentences overlap slightly in restating the smart_recall contrast, which is minor redundancy rather than wasted space.

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

Completeness3/5

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

For a simple three-parameter read tool with no output schema and no annotations, the description covers purpose, scope, and selection guidance adequately. The notable gap is return-shape behavior (what a hit looks like, ranking, how limit interacts with the default of 15), which is not covered by an output schema or annotations.

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 all three parameters are already documented (query, limit with default 15, instance_id). The description adds no per-parameter meaning such as query syntax, phrase/boolean support, or what instance_id scopes to. Baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb and mechanism ('BM25+ full-text search') plus an explicit resource scope ('ALL brain data: lessons, context entries, session history, CKG nodes, roadmap items'). It directly contrasts with the sibling smart_recall, so an agent can distinguish the two without opening either schema.

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?

Gives a clear selection rule: use this when smart_recall returns nothing, or when the goal is open-ended discovery of anything the brain knows. The named alternative and its narrower focus ('lessons + context') make the routing decision concrete. It stops short of an explicit when-not beyond the smart_recall comparison.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.