Skip to main content
Glama
Sign In

I Am Wallet

by io.github.ZKStamp
OverviewDiscussionsAdmin

deal_deliver

DEALS (seller): deliver the NEXT step after it was paid (1 confirmation). Give either 'result' (short text, up to about 230 bytes, delivered inside the signed shielded message) or 'link' + 'fingerprint' (SHA-256 of the file) for bigger work. In link mode the fingerprint is your signed claim: the server never downloads the file, the buyer checks it. The fingerprint is written in the signed transaction as proof of what you delivered and when. Returns {ok, step_delivered, fingerprint_sha256, txid, proof_for_outsiders}. Shielded on the blockchain. Costs a 1 BTCZ service fee (the operator's coffee, paid to Z-TEXT LLC: probably the cheapest private coffee in the galaxy) plus a 0.0001 BTCZ network fee. Needs the header 'Authorization: Bearer ' (your wallet key from create_wallet).

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": {
      "deal_id": "<deal_id>"
    },
    "name": "deal_deliver"
  }
}

Input Schema

NameRequiredDescriptionDefault
linkNoLink to a bigger result (stored outside the blockchain)
resultNoShort result delivered inside the message
deal_idYesThe deal id
fingerprintNoSHA-256 (64 hex) of the file behind the link

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the required 'Authorization: Bearer <key>' header, both fees (1 BTCZ service fee plus 0.0001 BTCZ network fee), the privacy model ('shielded on the blockchain', server never downloads the file in link mode), and the ledger effect (fingerprint written into the signed transaction as proof). It even lists the return keys, which is more than most write tools offer.

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 and dense: purpose and precondition first, then mode selection, then return shape, cost and auth. One sentence is wasted on the 'cheapest private coffee in the galaxy' aside, which adds bytes without helping an agent invoke the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter write tool with no annotations and no output schema, everything needed to call it correctly is present: auth, cost, precondition, mode selection, byte limit, and an inline listing of the returned fields. Only retry/idempotency and error behavior are left unstated, which is a small residual gap.

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 the schema lacks: the either/or constraint between 'result' and 'link'+'fingerprint', the ~230-byte size limit on 'result', and the fact that the fingerprint is the seller's signed claim rather than a server-verified hash. 'deal_id' is left to the schema, which is a minor omission only.

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?

Names a specific verb and resource ('deliver the NEXT step' of a deal) and scopes the actor ('DEALS (seller)') plus the precondition ('after it was paid (1 confirmation)'). This is enough to separate it from deal_pay, deal_offer, deal_check and deal_status without opening any 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?

Gives a clear when-to-use rule (after payment, one confirmation) and states how to choose between the two delivery modes: 'result' for short text, 'link' + 'fingerprint' for bigger work. It stops short of naming a sibling to check status first (e.g. deal_status), so the exclusions are implied rather than explicit.

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

All I Am Wallet 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