Skip to main content
Glama
agent-context-bridge

agent-context-bridge

acb_search

Read-onlyIdempotent

Search the shared agent context store to find prior decisions, tags, and notes before acting. Runs read-only, case-insensitive full-text queries over topics, summaries, details, and tags, newest-first.

Instructions

Read-only full-text search over the shared agent context store (.agent_bridge/records.jsonl). OR-combined case-insensitive match on topic/summary/details/tags, newest-first. Never writes or prunes; use to find prior decisions before acting. Returns {version, command, query, count, results[], skipped}.

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": "acb_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
dirNoOptional workspace path confined under the server --dir root; outside root rejected (-32602). Default: server cwd.
tagNoOptional tag filter list, e.g. ['db']; ANDed with query.
agentNoOptional agent-name filter, exact case-insensitive match, e.g. 'hermes-dev'.
limitNoMax hits 1..100, default 10, newest-first.
queryYes1+ words, OR-combined, case-insensitive; e.g. 'auth decision'. Required, non-empty.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.2

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and closed-world, so the safety profile is covered structurally. The description reinforces this with 'Never writes or prunes' and adds genuinely new behavior (newest-first ordering, OR matching across four fields, and the response shape), but the ordering/scoping additions are modest given how much the annotations already carry.

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 tight sentences: identity and scope first, matching behavior second, safety and intended use third, with the return shape compactly enumerated. No filler or repetition.

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?

With no output schema, the description usefully enumerates the return keys ({version, command, query, count, results[], skipped}), and all parameters are documented. The one loose end is that 'skipped' is listed without explanation of what causes results to be skipped.

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, and the description earns above that by specifying which record fields the 'query' parameter actually matches against — information the schema does not provide. It also explains the newest-first ordering that governs 'limit', though it does not clarify whether 'tag'/'agent' filters compose with the OR logic or narrow it.

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 resource: 'full-text search over the shared agent context store', naming the underlying file (.agent_bridge/records.jsonl) and the match semantics (OR-combined, case-insensitive, over topic/summary/details/tags). This is clearly distinct from a status tool like acb_status without needing to inspect 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 an explicit use case: 'use to find prior decisions before acting', which tells the agent when this tool is appropriate. It does not state when-not to use it or name acb_status as the alternative for status checks, so it falls short of full routing guidance.

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