Skip to main content
Glama
Sign In
Antigravity Truth Guard

Antigravity Truth Guard

by bushold-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

truth_search

Search indexed ground-truth rules, architecture specs, and schema contracts to ground code changes in verified project facts, with zero Firestore reads.

Instructions

RAM mirror semantic search for ground-truth rules, architecture specs, and schema contracts (0 Firestore reads)

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": "truth_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesSearch query describing the feature, rule, or schema to look up
include_globalNoWhether to also search the global rules catalog
target_projectNoOptional specific project_id to search instead of current project

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.1.0

TDQS

B3.4/5.0
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 two useful behavioral facts — results come from an in-memory RAM mirror and incur zero Firestore reads — which hints at a cached, possibly stale snapshot and a read-only operation. It never states staleness/refresh semantics, ranking or result limits, or what happens when the mirror is unpopulated, which matters for a tool whose whole value proposition is freshness-free lookup.

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?

A single compact sentence with the resource and the differentiating trait (RAM mirror, 0 Firestore reads) front-loaded and no filler. The parenthetical is terse but the jargon is dense enough that a first-time reader may need a beat to parse 'RAM mirror'.

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 three-parameter read tool with no output schema, the description covers purpose and data source but says nothing about what comes back — ranked snippets, matched rule documents, scores, or counts. Return-shape ambiguity is the main gap, since nothing else in the structured data compensates for it.

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 (query, include_global, target_project) are already documented in the schema, establishing a baseline of 3. The description adds only corpus context for what a query should describe (feature, rule, or schema), with nothing extra about include_global or target_project beyond the schema text.

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?

The description names a specific verb and resource: semantic search over ground-truth rules, architecture specs, and schema contracts. The 'RAM mirror ... (0 Firestore reads)' qualifier makes the retrieval path distinguishable from a live-database lookup. It stops short of explicitly contrasting with siblings like truth_status or truth_upsert_rule.

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

Usage Guidelines3/5

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

Usage is only implied: an agent can infer this is the read path for looking up existing rules/specs before acting. There is no explicit when-to-use framing, no statement of when not to use it, and no pointer to truth_upsert_rule for adding rules or truth_status for catalog state.

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