Skip to main content
Glama

unified_search

Search all OS knowledge (task memos, reports, tasks) using fused BM25, knowledge-graph fanout, and exact ID matching to recall past work, commit hashes, or wf_ IDs.

Instructions

Search across all OS knowledge: task memos, reports, and tasks.

Three-arm RRF fusion (k=60): BM25 full-text (Chinese bigram native), knowledge-graph fanout (queries containing wf_/commit/uuid IDs pull in everything linked to them), and exact ID-prefix / title match.

Use this to recall past work: "how was the ownership iron rule fixed", "wf_d01f207f", "stderr blind spot", commit hashes, etc.

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": "unified_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax results (default 10)
queryYesFree text or an OS ID (wf_id / commit / task uuid)
project_idNoRestrict to one project (empty = all)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.11.2

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are provided, so the description carries the burden, and it does disclose real mechanics: three-arm RRF fusion with k=60, BM25 with Chinese bigram handling, knowledge-graph fanout triggered specifically by wf_/commit/uuid IDs, and exact ID-prefix/title matching. That is meaningful beyond a bare 'search' claim, but it omits read-only status, result truncation/ranking-cutoff behavior at the limit, and any cost or latency characteristics, leaving the operational profile partly uncovered.

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 purpose, then mechanism, then concrete example queries, with no filler sentences. The 'k=60' parameter is low-value jargon for an agent and the whitespace-broken sentence adds slight friction, but overall it is tight and well ordered.

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?

An output schema exists, so return shape need not be explained, and all three parameters are documented in the schema. For a moderately complex hybrid-retrieval tool the description covers what it searches, how ranking is composed, and when special fanout kicks in; the remaining gap is behavior at the limit and whether results are truncated or scored.

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 100%, so the baseline is 3, but the description adds genuine semantics beyond the schema: queries containing wf_/commit/uuid IDs trigger knowledge-graph fanout that pulls in everything linked to those entities, which changes what a query string means. It also corroborates that query accepts free text or an OS ID, though limit and project_id gain nothing additional.

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?

States a specific verb and resource plus an explicit scope: 'Search across all OS knowledge: task memos, reports, and tasks.' The scope ('all OS knowledge') implicitly separates it from narrower siblings such as memory_search or ecosystem_search, but no sibling is named, so differentiation is inferred rather than stated.

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 use context ('Use this to recall past work') reinforced with three concrete example queries, including an ID-shaped one, which tells the agent what kinds of inputs belong here. It stops short of when-not guidance or naming an alternative search tool for narrower cases.

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

Deploy Server

Other Tools