groundlens

Official

Overview Schema Source Related Servers Discussions Admin

verify_answer

Check an answer against its source passages before sending, ensuring every figure is grounded. Returns PASS, REVIEW or FAIL with reasons and a signed evidence record.

Instructions

Check an answer against the passages it was written from, before you send it.

    Every figure must be in the passages or follow from figures that are; no model
    is used. Returns PASS, REVIEW or FAIL with the reasons, and the signed record.

    sources: (id, text) pairs, {"id","text","provenance"} dicts, or bare strings.
    policy: a built-in name (e.g. "eu_ai_act_high_risk_v1"), a path, or YAML.
    scope: what the request is about, e.g. {"entity": "UPS"}; a figure taken
    from a source whose provenance is another entity fails.
    risk_class: the request's risk class, when the policy defines them.
    Returns the decision (PASS/REVIEW/FAIL), the evidence, the regulatory
    mapping and the record with its content hash.

Input Schema

Name	Required	Default
`scope`	No
`answer`	Yes
`locale`	No	und
`policy`	No
`sources`	Yes
`question`	No
`risk_class`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv6.0.2Oct 15, 2026

addedInput schema / properties / risk_class

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Risk Class"
+}

addedInput schema / properties / scope

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Scope"
+}

Addedv3.0.6Sep 21, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does real work: it discloses that 'no model is used' (deterministic, rule-based), the three-outcome decision space, that reasons/evidence/regulatory mapping are produced, and that a signed record with a content hash is emitted. It does not mention auth requirements, rate limits, or cost, which keeps it short of a 5.

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 purpose, then behavioral summary, then parameter notes – a sensible order. The only waste is the duplicated return description ('Returns PASS, REVIEW or FAIL with the reasons, and the signed record' vs 'Returns the decision ... the evidence, the regulatory mapping and the record with its content hash').

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 7-parameter tool with an output schema, the description covers the semantically hard inputs (sources, policy, scope, risk_class) and the decision model. Because an output schema exists it need not re-explain returns, and it partially does anyway. The gaps are minor: question and locale are never described, and no sibling disambiguation is offered.

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 0%, so the description must compensate, and it largely does: sources is given three concrete accepted shapes, policy lists built-in name/path/YAML forms, scope is explained with an example plus the cross-entity failure rule, and risk_class is tied to policy-defined classes. The question and locale parameters remain unexplained in both schema and description.

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 pair (check an answer against its source passages) with the timing constraint 'before you send it'. It is clear on its own, but it never names or distinguishes itself from the siblings verify_run and verify_records, so an agent cannot route between the three from the description alone.

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?

'before you send it' implies the workflow position (pre-publication gate), which is useful. However, there is no statement of when NOT to use it, no prerequisites (e.g. whether sources must be pre-chunked), and no routing to verify_run or verify_records, so the guidance is only implied.

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

Deploy Server