Skip to main content
Glama

Verify a proof file

symbolon_verify_proof
Read-only

Verifies a proof file produced by an agent wallet: agent signatures, owner mandates and published owner keys, presence in this register, revealed clauses, amount limits and, when present, the Bitcoin anchor. Returns each check. Read-only.

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": {
      "proof": "<proof>"
    },
    "name": "symbolon_verify_proof"
  }
}

Input Schema

NameRequiredDescriptionDefault
proofYesThe proof file (JSON object)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already supply readOnlyHint and openWorldHint, so the safety profile is covered, and the description goes further by listing the concrete checks performed and stating 'Returns each check', which tells the agent the result is a per-item report rather than a single boolean. It stops short of describing outcome semantics (is a failed verification an error or a returned status?) or cost/latency for the anchored case, so it is not fully transparent.

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?

The core content is one front-loaded sentence with a well-ordered list of checks, followed by a short result statement. The trailing 'Read-only.' duplicates the readOnlyHint annotation and slightly blunts the ending, but overall the text is dense and earns its space.

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?

With no output schema and a nested, free-form 'proof' object, the description should do more than 'Returns each check' — it omits the shape of the result (per-check names, pass/fail values) and what a negative verification means for the caller. It covers inputs and scope well but leaves the return contract underspecified for a tool whose entire value is its verdict.

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?

The schema documents the single 'proof' parameter only as an opaque JSON object, so the baseline would be 3 at 100% coverage. The description compensates by revealing what the proof payload must contain (agent signatures, owner mandates, published owner keys, clauses, amount limits, Bitcoin anchor), which helps the agent recognize a valid input file rather than a report or wrapper.

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 opens with a specific verb+resource ('Verifies a proof file produced by an agent wallet') and then enumerates exactly what is checked: signatures, mandates, owner keys, register presence, clauses, amount limits and the optional Bitcoin anchor. This is precise enough to separate it from siblings like symbolon_check_counterparty or symbolon_lookup_fingerprint, which operate on different inputs.

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 phrase 'proof file produced by an agent wallet' plus 'Read-only', so an agent can infer this is the validation step for a received proof. However, there is no explicit statement of when to call this versus the sibling check tools, no prerequisites (e.g. proof must be unmodified JSON as received), and no guidance on what to do after a failed check.

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.