Skip to main content
Glama
VeritasGraph

VeritasGraph

by bibinprathap

veritasgraph_query

Ask a natural-language question to get a graph-grounded, multi-hop answer with verifiable citations and a reasoning path; abstains when no evidence exists.

Instructions

Ask a question and get a graph-grounded, multi-hop answer with verifiable [doc#chunk] citations, a grounded flag, the reasoning path and an answer_id receipt. Abstains when the graph has no evidence.

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": {
      "question": "<question>"
    },
    "name": "veritasgraph_query"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNogoverned: only answer when certified glossary terms cover the question, and withhold answers whose citations are not in the retrieved evidence.
modelNoLocal Ollama model to use (defaults to $VERITASGRAPH_MODEL).
questionYesNatural-language question.
max_depthNoMax graph hops (default 2).
max_nodesNoMax subgraph nodes (default 25).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.0
    • addedInput schema / properties / mode
      Added value: +{
      +  "description": "governed: only answer when certified glossary terms cover the question, and withhold answers whose citations are not in the retrieved evidence.",
      +  "enum": [
      +    "exploratory",
      +    "governed"
      +  ],
      +  "type": "string"
      +}
  2. First observedv0.1.2

TDQS

B3.3/5.0
Behavior3/5

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

No annotations exist, so the description carries the burden, and it does disclose the response shape and the abstention behavior, which is useful. It says nothing about cost, latency, permissions, or what happens when mode is exploratory versus governed, and the schema is the only place the governed/certified-terms behavior is described. Useful but incomplete for a tool with zero annotation coverage.

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?

Two sentences, front-loaded with the verb and the response artifacts, with no filler. The abstention clause earns its place because it changes what an agent should expect back.

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 five-parameter retrieval tool with no annotations and no output schema, the description usefully enumerates the returned fields, so an agent knows what it gets back. It still omits the parameter tradeoffs (hop depth, node budget), the meaning of the governed mode, and any sibling differentiation, leaving gaps against the tool's complexity.

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 the schema already explains mode, model, max_depth and max_nodes in detail. The description adds nothing about any parameter; the governed-mode behavior is documented in the schema, not here. Baseline 3 applies since the schema does the work.

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 ('ask a question') and resource ('graph-grounded, multi-hop answer') and names the return artifacts: [doc#chunk] citations, a grounded flag, a reasoning path and an answer_id. That is far more concrete than the title alone. It does not, however, distinguish itself from similar siblings such as veritasgraph_structured_ask or veritasgraph_check_answerable, so an agent must still guess which retrieval tool fits.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance at all. The one behavioral clause, 'Abstains when the graph has no evidence', describes an outcome rather than a condition for selection. With a catalog containing structured_ask and check_answerable, the omission of routing advice is a real gap.

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