Skip to main content
Glama

Verify signed AI-agent authorization and execution evidence

agent_proof_verify
Read-only

Verify that two independently signed records agree on one authorized, completed action. $0.01 USDC via x402 per successful verification. Does not independently prove real-world execution or key ownership.

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": {
      "authorization": "<authorization>",
      "acknowledgment": "<acknowledgment>",
      "trusted_keys": "<trusted_keys>"
    },
    "name": "agent_proof_verify"
  }
}

Input Schema

NameRequiredDescriptionDefault
trusted_keysYesOut-of-band pinned policy and executor Ed25519 public keys; never private keys
authorizationYesEd25519-signed policy decision envelope; hashes and identifiers only
acknowledgmentYesSeparately signed executor acknowledgment binding the authorization digest

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds two behavioral facts annotations cannot: a per-successful-verification charge of $0.01 USDC via x402 (implying billing only on success) and a bounded trust claim — it does not prove real-world execution or key ownership. That scope caveat is the kind of context an agent needs before treating a pass as ground truth.

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?

Three short sentences, front-loaded with the core action, followed by cost and then the limitation. Every sentence carries distinct load — no restatement of the title or name. Nothing could be removed without losing either scope, price, or caveat information.

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?

There is no output schema, so the description should indicate what a verification returns — a boolean, a mismatch reason, per-field agreement details — and it does not. For a verification tool whose entire value is the verdict, that is a real gap. The trust boundary and cost model are well covered, so it is adequate rather than complete.

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 defines trusted_keys as out-of-band pinned Ed25519 public keys, authorization as a signed policy decision envelope, and acknowledgment as a separately signed executor acknowledgment binding the authorization digest. The description reinforces the relationship between the two envelopes but adds no format, encoding, or sizing detail beyond the schema. 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?

The description states a specific verb and object: verify that two independently signed records (authorization + acknowledgment) agree on one authorized, completed action. That is far more precise than a generic 'verify proof' claim and maps cleanly onto the two signed-envelope parameters. It stops short of naming any sibling tool or explaining how it differs from adjacent verification tools like passport_verify or qledger_verify_chain.

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 implied by the shape of the input (call it when you hold both a signed authorization and a signed acknowledgment) and by the explicit negative scope statement about what it does not prove. However, there is no explicit when-to-use/when-not-to-use guidance and no routing to alternatives when only one signed record is available. The agent must infer the entry condition.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources