GREENLANDAI

verify_proof

Read-only

Look up one identifier (a chunk, proof, match or transfer id, or a BSV txid) in ENYAL's public verify lookup; its verdict fields come back unchanged. Only chain_confirmed:true is a verified anchor; degraded:true means inconclusive, not absent. No auth.

Input Schema

Name	Required	Description	Default
`identifier`	Yes	The id to look up: a chunk_id, proof_id, match_id or transfer id (UUID), or a BSV transaction id (64 hex).

Output Schema

Name	Required	Description	Default
`note`	No
`count`	No
`found`	No
`results`	No
`degraded`	No
`recorded`	No
`identifier`	No
`chain_status`	No
`chain_confirmed`	No
`unavailable_sources`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed30 schema fields changedOct 29, 2026
- removedInput schema / properties / identifier / title
```
Removed value: -"Identifier"
```
- removedInput schema / title
```
Removed value: -"verify_proofArguments"
```
- removedOutput schema / description
```
Removed value: -"verify_proof — the ENVELOPE only. `results` is an OPAQUE list and must stay that way: every\nper-record verdict field lives inside it, including `release_anchor_status` (11 values) and the\ntwo independent anchors (ledger_payout_anchor, escrow_contract_release_anchor). Modelling the\ninner records would risk collapsing or refusing an enum value, which is precisely the false\ncertainty this tool exists to prevent. Read the envelope for reachability, the records for verdicts."
```
- removedOutput schema / properties / chain_confirmed / default
```
Removed value: -null
```
- removedOutput schema / properties / chain_confirmed / description
```
Removed value: -"only true is a verified anchor"
```
- removedOutput schema / properties / chain_confirmed / title
```
Removed value: -"Chain Confirmed"
```
- removedOutput schema / properties / chain_status / default
```
Removed value: -null
```
- removedOutput schema / properties / chain_status / description
```
Removed value: -"bare-txid lookups: confirmed|mempool|not_on_chain|unchecked"
```
- removedOutput schema / properties / chain_status / title
```
Removed value: -"Chain Status"
```
- removedOutput schema / properties / count / default
```
Removed value: -null
```
- removedOutput schema / properties / count / title
```
Removed value: -"Count"
```
- removedOutput schema / properties / degraded / default
```
Removed value: -null
```
- removedOutput schema / properties / degraded / description
```
Removed value: -"true = INCONCLUSIVE, never an absence"
```
- removedOutput schema / properties / degraded / title
```
Removed value: -"Degraded"
```
- removedOutput schema / properties / found / default
```
Removed value: -null
```
- removedOutput schema / properties / found / description
```
Removed value: -"a record exists in at least one source"
```
- removedOutput schema / properties / found / title
```
Removed value: -"Found"
```
- removedOutput schema / properties / identifier / default
```
Removed value: -null
```
- removedOutput schema / properties / identifier / title
```
Removed value: -"Identifier"
```
- removedOutput schema / properties / note / default
```
Removed value: -null
```
- removedOutput schema / properties / note / title
```
Removed value: -"Note"
```
- removedOutput schema / properties / recorded / default
```
Removed value: -null
```
- removedOutput schema / properties / recorded / description
```
Removed value: -"we hold it even if the chain does not"
```
- removedOutput schema / properties / recorded / title
```
Removed value: -"Recorded"
```
- removedOutput schema / properties / results / default
```
Removed value: -null
```
- removedOutput schema / properties / results / description
```
Removed value: -"per-record verdicts, passed through untouched"
```
- removedOutput schema / properties / results / title
```
Removed value: -"Results"
```
- removedOutput schema / properties / unavailable_sources / default
```
Removed value: -null
```
- removedOutput schema / properties / unavailable_sources / title
```
Removed value: -"Unavailable Sources"
```
- removedOutput schema / title
```
Removed value: -"VerifyOut"
```

Changed1 schema field changedOct 17, 2026

addedInput schema / properties / identifier / description

Added value: +"The id to look up: a chunk_id, proof_id, match_id or transfer id (UUID), or a BSV transaction id (64 hex)."

Changed1 schema field changedSep 20, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "verify_proof — the ENVELOPE only. `results` is an OPAQUE list and must stay that way: every\nper-record verdict field lives inside it, including `release_anchor_status` (11 values) and the\ntwo independent anchors (ledger_payout_anchor, escrow_contract_release_anchor). Modelling the\ninner records would risk collapsing or refusing an enum value, which is precisely the false\ncertainty this tool exists to prevent. Read the envelope for reachability, the records for verdicts.",
+  "properties": {
+    "chain_confirmed": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "only true is a verified anchor",
+      "title": "Chain Confirmed"
+    },
+    "chain_status": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "bare-txid lookups: confirmed|mempool|not_on_chain|unchecked",
+      "title": "Chain Status"
+    },
+    "count": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Count"
+    },
+    "degraded": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "true = INCONCLUSIVE, never an absence",
+      "title": "Degraded"
+    },
+    "found": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "a record exists in at least one source",
+      "title": "Found"
+    },
+    "identifier": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Identifier"
+    },
+    "note": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Note"
+    },
+    "recorded": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "we hold it even if the chain does not",
+      "title": "Recorded"
+    },
+    "results": {
+      "anyOf": [
+        {
+          "items": {},
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "per-record verdicts, passed through untouched",
+      "title": "Results"
+    },
+    "unavailable_sources": {
+      "anyOf": [
+        {},
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Unavailable Sources"
+    }
+  },
+  "title": "VerifyOut",
+  "type": "object"
+}

First observedSep 14, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint and non-destructive behavior, and the description adds useful context beyond them: it says the lookup is public with no auth and that verdict fields come back unchanged. It also clarifies the meaning of chain_confirmed and degraded, which is important for correct interpretation.

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?

The description is two dense sentences with no filler. The lookup scope is front-loaded, followed by the key interpretation rules and the no-auth note, so every clause earns its place.

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?

The tool is simple, has one fully documented parameter, and has an output schema, so the description need not explain return values. It covers the critical semantic caveats (chain_confirmed vs degraded) and the no-auth behavior, leaving only minor details unstated.

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?

The schema has 100% description coverage for the single identifier parameter, including the accepted ID formats. The description repeats those identifier types but does not add syntax or format details beyond what the schema already provides, so baseline 3 applies.

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 (look up) and resource (ENYAL's public verify lookup) and enumerates the identifier types it accepts. It is clear what the tool does, though it does not explicitly differentiate itself from sibling proof tools such as balance_proof or bridge_proof.

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?

The description implies the tool is for checking the verification status of an identifier, and explains how to interpret verdict fields. However, it gives no explicit when-to-use guidance or points to alternative sibling tools for related proof or ledger verification tasks.

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

All GREENLANDAI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?