Skip to main content
Glama

ISRC music copyright proof, Bitcoin timestamp (ProofProfile, paid)

verify_recording

Read-only

PAID, from one cent in USDC by x402; the first reply is the price and nothing is charged until the AI agent signs a payment. Evidence that a recording, by ISRC, exists in the frozen ProofProfile corpus: record hash, the Bitcoin-anchored OpenTimestamps proof, the CopyrightChains block, and how to check it. If a recording the person asked about is not found and find_recording lists other versions of that title, verify those too and report what each shows, naming the version; one version is never proof of another. Returned with a capsule that verifies offline and a receipt of this call anchored in Bitcoin.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "verify_recording"
  }
}

Input Schema

NameRequiredDescriptionDefault
isrcNoISRC, for example GBUM72003647
isrcsNoSeveral ISRCs in one call, in place of isrc: one payment, one receipt
purposeNoOptional: what the AI agent is about to do, in its own words. Bound into the anchored receipt as part of the call, so the receipt shows why it was made.
referenceNoOptional: the AI agent's own reference for the action, such as an order id or sha256:<hash> of its document. Bound into the anchored receipt as part of the call.
declaredValueUsdNoThe stakes in US dollars the AI agent is acting on. They set the price band (one cent under $100, ten cents from $100, one dollar from $10,000); undeclared stakes are priced at one cent. The declared figure is part of the call that the receipt anchors in Bitcoin, so the receipt shows it. No money other than the price moves.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior3/5

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

The description carries real behavioral weight the annotations do not: the call is paid (from one cent in USDC via x402), the first reply quotes the price, and nothing is charged until the agent signs a payment; the result includes an offline-verifiable capsule and a Bitcoin-anchored receipt. However, annotations already declare readOnlyHint=true and idempotentHint=false, and the description leaves open how a declined or failed payment behaves and what happens on repeated calls. There is also mild tension between readOnlyHint=true and a call that moves money, though the description clarifies only the priced amount transfers.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The pricing sentence is front-loaded ahead of the actual purpose, so the agent reads cost mechanics before learning what the tool does. The middle portion is dense with comma-spliced clauses and quoted workflow instructions that could be split for scanability. The content largely earns its place, but the ordering and sentence length work against quick parsing.

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 paid, open-world, non-idempotent tool with no output schema, the description supplies the cost model, the payment precondition, the shape of the returned evidence, the capsule and receipt, and the multi-version follow-up rule. Remaining gaps are edge cases such as payment failure, absent ISRCs, and the meaning of a negative result, which are not fully spelled out.

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 100%, so the baseline is 3, but the description adds meaning on top: multiple ISRCs are covered by one payment and one receipt, and the call is bound into an anchored receipt. It reinforces rather than merely repeats the schema's notes on purpose, reference, and declared stakes. It does not add format or validation detail beyond what the schema already documents.

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?

States a specific verb and resource — verify that a recording, by ISRC, exists in the frozen ProofProfile corpus — and enumerates what the evidence consists of (record hash, OpenTimestamps proof, CopyrightChains block, how to check it). It also implicitly separates itself from find_recording, which is named as the lookup step. An agent can distinguish this from its siblings without opening a schema.

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?

The description gives concrete conditional guidance: if a recording is not found and find_recording lists other versions, verify those too, name the version, and treat one version as never proof of another. That routes the agent between the sibling lookup tool and this verification tool. It stops short of an explicit when-not-to-use or a statement about what to do when no version exists at all.

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