Skip to main content
Glama

Search Brain (passages, slow + billed)

flypost_search_brain
Read-only

LAST RESORT. Passage-level Brain search that runs a server-side LLM to extract quotes — 20–40s and it bills the user's AI budget. Use flypost_search_source_docs first: it returns the full source documents for the same query in ~2s at no AI cost, and you can pick the quotes out yourself. Only fall back to this tool if those documents were genuinely insufficient.

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": "flypost_search_brain"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesWhat to look for, phrased as a topic or question.
match_countNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the readOnly/non-destructive annotations, the description discloses the two traits that actually matter here: 20–40s latency and billed consumption of the user's AI budget, plus the reason (server-side LLM extraction). It also indicates the return shape is extracted quotes rather than documents.

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 the highest-stakes signal ("LAST RESORT"), then the cheap alternative, then the gating condition. No sentence is redundant; cost and latency are packed into a single clause.

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 2-parameter tool with no output schema, the description covers cost, latency, mechanism, result form (quotes), and the decision path. The only gap is result cardinality and how `match_count` shapes output, which is a minor omission given the otherwise strong guidance.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 50%: `match_count` has bounds (1–25) but no description anywhere, and the description says nothing about it — not how many passages it controls, its default, or how it interacts with quote extraction. The description adds no parameter meaning beyond the schema's own text for `query`.

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?

"Passage-level Brain search that runs a server-side LLM to extract quotes" is a specific verb + resource + mechanism, and the opening "LAST RESORT" plus the named contrast with flypost_search_source_docs makes it unmistakable from its sibling.

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?

It names the preferred alternative (flypost_search_source_docs), the condition to try it first (full source documents, ~2s, no AI cost), and the explicit fallback condition (documents genuinely insufficient). Both when-to-use and when-not-to-use are stated.

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.