Skip to main content
Glama

Invoicing mandate (level 3)

seller.mandate
Destructive

Admin agents and owners. get shows the mandate text (link, version, sha256) and whether it is signed. sign: first call returns a challenge, sign it with your wallet and call again with agreement_proof {message, signature}. Then, with a listing on level 2 and Books, buyers on level 3 get monthly invoices in your name (§ 14 (2) UStG), issued by 402lounge. revoke ends it at the end of the month.

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": {
      "action": "<action>"
    },
    "name": "seller.mandate"
  }
}

Input Schema

NameRequiredDescriptionDefault
proofNoAn EIP-4361 message you got from a challenge, signed by your wallet
actionYesget shows the text and whether it is signed, sign signs it (a challenge first), revoke ends it at the end of the month
clientNoYour client name, e.g. "claude-code 2.1"
confirmNosign: true, after you read the mandate text from get
session_tokenNoA lounge session token (lg_...) if you have one
agreement_proofNosign, second call: the challenge message the first call returned, and your wallet's signature over it

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / action / description
      Added value: +"get shows the text and whether it is signed, sign signs it (a challenge first), revoke ends it at the end of the month"
    • addedInput schema / properties / agreement_proof / description
      Added value: +"sign, second call: the challenge message the first call returned, and your wallet's signature over it"
    • addedInput schema / properties / confirm / description
      Added value: +"sign: true, after you read the mandate text from get"
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare destructiveHint=true and idempotentHint=false, and the description earns its keep by disclosing the two-phase challenge/signature protocol and, crucially, that revoke takes effect at the end of the month rather than immediately — a non-obvious timing trait. It also discloses the downstream legal consequence (invoices issued in the seller's name by 402lounge). It does not state whether signing is reversible before month end or what happens to already-issued invoices on revoke.

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?

Front-loaded with the audience, then one clause per action in the order get/sign/revoke, with the signing flow given the most space because it is the multi-step path. The opening 'Admin agents and owners.' is a fragment and the legal citation is compressed to near-opacity, but no sentence is filler.

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 six-parameter, nested-object mutation tool with no output schema, the description covers what get returns, how sign sequences, and when revoke lands, which is the bulk of what an agent needs. The residual gap is the confirm-after-reading contract and the consequences of revoking an already-active mandate, neither of which is spelled out in prose.

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; the description clears that bar by explaining the sequence behind agreement_proof and that the first sign call returns a challenge the second consumes. It says nothing about client, session_token, or the confirm gate, leaving those entirely to the schema — acceptable given full coverage, but it means the description adds no safety framing around confirm.

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 the resource (the invoicing mandate) and enumerates the three distinct sub-actions with their effect: get returns link/version/sha256 and signed status, sign runs a challenge-then-proof sequence, revoke terminates at month end. Each action is distinguishable without opening the schema, and the legal framing (§ 14 (2) UStG, issued by 402lounge) pins down what the mandate actually is.

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 states the audience (admin agents and owners) and the precondition for the signing path (listing on level 2 plus Books, buyers on level 3), and it prescribes the ordering of the two sign calls. What it does not do is point at any sibling tool — e.g. seller.self_billing or lounge.terms — so an agent must infer that this mandate is the prerequisite for self-billing rather than an alternative to it.

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