Skip to main content
Glama

Lovie Company Formation

by co.lovie
OverviewDiscussionsAdmin

Extract Wire Payment Proof

cap_table_extract_wire_payment_proof

Runs vision OCR on an already-uploaded wire payment proof (wire confirmation, bank statement, or transfer receipt — NOT an invoice) for a security and returns the extracted fields plus a verification verdict (verified | needs_review | mismatch). Nothing is persisted. Flow: call GetOcrUploadURL with kind=WIRE_PROOF, PUT the file bytes to the returned upload_url, then call this with the returned source_s3_uri. Only a 'verified' verdict can back a wire in RecordCapTableWire.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agentCodeNo
companyIdYesUUID value wrapper.
securityIdYesUUID value wrapper.
sourceS3UriNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
proofNo
warningsNo
sourceS3UriNo
verificationNo
ocrConfidenceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedOutput schema / properties / proof / anyOf
      Added value: +[
+  {
+    "properties": {
+      "amount": {
+        "type": "string"
+      },
+      "bankName": {
+        "type": "string"
+      },
+      "currencyCode": {
+        "type": "string"
+      },
+      "documentType": {
+        "type": "string"
+      },
+      "isPaymentProof": {
+        "type": "boolean"
+      },
+      "recipientAccountLast4": {
+        "type": "string"
+      },
+      "recipientName": {
+        "type": "string"
+      },
+      "reference": {
+        "type": "string"
+      },
+      "senderName": {
+        "type": "string"
+      },
+      "transferDate": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedOutput schema / properties / proof / properties
      Removed value: -{
-  "amount": {
-    "type": "string"
-  },
-  "bankName": {
-    "type": "string"
-  },
-  "currencyCode": {
-    "type": "string"
-  },
-  "documentType": {
-    "type": "string"
-  },
-  "isPaymentProof": {
-    "type": "boolean"
-  },
-  "recipientAccountLast4": {
-    "type": "string"
-  },
-  "recipientName": {
-    "type": "string"
-  },
-  "reference": {
-    "type": "string"
-  },
-  "senderName": {
-    "type": "string"
-  },
-  "transferDate": {
-    "type": "string"
-  }
-}
    • removedOutput schema / properties / proof / type
      Removed value: -"object"
    • addedOutput schema / properties / verification / anyOf
      Added value: +[
+  {
+    "properties": {
+      "amountMatches": {
+        "type": "boolean"
+      },
+      "isPaymentProof": {
+        "type": "boolean"
+      },
+      "nameMatches": {
+        "type": "boolean"
+      },
+      "reasons": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "status": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedOutput schema / properties / verification / properties
      Removed value: -{
-  "amountMatches": {
-    "type": "boolean"
-  },
-  "isPaymentProof": {
-    "type": "boolean"
-  },
-  "nameMatches": {
-    "type": "boolean"
-  },
-  "reasons": {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  "status": {
-    "type": "string"
-  }
-}
    • removedOutput schema / properties / verification / type
      Removed value: -"object"
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotations, it discloses that nothing is persisted, that the input must already be uploaded, and that the response contains extracted fields plus a verified/needs_review/mismatch verdict. This meaningfully supplements the minimal annotation set and does not contradict it.

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 compact and front-loaded, with the core action first, followed by a precise upload flow and a downstream usage constraint. Every sentence 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?

Given the output schema and annotations, the description covers the main call flow, return verdicts, non-persistence, and downstream gating. Minor gaps remain around agentCode and companyId semantics, but they do not block correct invocation.

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 description explains sourceS3Uri as the output of the upload flow and 'for a security' hints at securityId, but companyId and agentCode receive no semantic help beyond the schema's sparse descriptions. With only 50% schema description coverage, the description only partially compensates for the gap.

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?

The description names a specific operation — vision OCR on an already-uploaded wire payment proof — and scopes it to wire-related evidence for a security, explicitly excluding invoices. This separates it from cap-table OCR and wire-recording siblings like cap_table_record_cap_table_wire.

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?

It gives a concrete workflow: call GetOcrUploadURL with kind=WIRE_PROOF, upload the file bytes, then pass the returned sourceS3Uri to this tool. It also states when results are usable — only a 'verified' verdict can back a wire — though it does not name a specific alternative tool for the excluded invoice case.

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

All Lovie Company Formation toolsInspect
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