Skip to main content
Glama
Sign In

proof-of-custody

by io.github.onrampbtc
OverviewDiscussionsAdmin

fit_custody_setup

Which bitcoin custody models fit a described situation, by Proof of Custody's published rules, and which platforms run each fitting model by published score. Inputs are banded (amount, who must recover it, what they can do, holder type, jurisdiction, usage, the failure feared most, willingness to let institutions hold keys, budget, where it is now). Returns models with every rule that fired, the recovery steps each model demands, platforms with source links, and the procurement briefs to run. Structures, not advice: it never picks one provider. Use for 'my spouse cannot run a hardware wallet, what works', 'custody for an LLC', 'I have 100 BTC on one device and three heirs', or any question that starts from a person's situation.

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": "fit_custody_setup"
  }
}

Input Schema

NameRequiredDescriptionDefault
fearNoThe failure that worries you most
amountNoHow much bitcoin
budgetNoCustody budget per year
holderNoWho holds it
currentNoWhere it is now
horizonNoHow you use it
recovererNoWho must be able to recover it if you cannot
capabilityNoWhat that person can do
institutionsNoInstitutions holding keys
jurisdictionNoWhere you are

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses that rules are 'published', that outputs include every fired rule, recovery steps, platforms with source links, and procurement briefs, and that it deliberately does not select a provider. Not stated are determinism, whether all inputs are optional, or how omitted bands are defaulted.

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 what the tool does, then outputs, then usage examples and the 'not advice' caveat. The parenthetical list of inputs is largely redundant with the schema and the opening sentence is long and dense, but overall every part carries signal.

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?

No annotations and no output schema, so the description must explain returns — which it does in detail (fired rules, recovery steps, scored platforms with source links, procurement briefs). The main remaining gap is that all ten parameters are optional yet the description never says what happens when inputs are omitted or partially supplied.

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 coverage is 100% and all ten parameters are documented enums, so the schema does the heavy lifting. The description's parenthetical listing of bands (amount, recoverer, capability, holder, jurisdiction, usage, fear, institutions, budget, current) restates the schema rather than adding meaning such as default behavior for omitted fields. Baseline 3 applies.

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+resource: it maps a described custody situation to fitting models under published rules, then to platforms and procurement briefs. It is clearly distinguishable from siblings like compare_custody_platforms and search_custody_platforms because it starts from a person's situation rather than from provider lists. The 'Structures, not advice: it never picks one provider' line further fixes its role.

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?

Provides concrete triggering examples ('my spouse cannot run a hardware wallet', 'custody for an LLC', '100 BTC on one device and three heirs') and a general rule ('any question that starts from a person's situation'). It also sets a boundary by saying it never recommends one provider. It does not name the alternative sibling tools by name, so routing against compare_custody_platforms is left implicit.

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

All proof-of-custody 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