pathiel

Overview Schema Source Related Servers Discussions Admin

leave_pool

Leave a research pool by first previewing the exact statement, then confirming with the returned timestamp to sign a leave file for a pull request; no order or money movement.

Instructions

Leave the research pool: the next scoreboard build drops your address and every row of it, and the leave stays in force until a later join. Two steps: without confirm it shows the exact statement and signs nothing; with confirm=true and the left_at that first call returned, it SIGNS that statement with your key and writes the leave file, which the user opens a pull request with, as for join_pool. No order is placed and no money moves. Call only when the user asked to leave, and confirm only after they read the statement; check membership first with get_pool_status. Needs a trading key and mainnet: on testnet it returns {error, code: testnet} and signs nothing. Returns the statement, then the signed leave file path.

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": "leave_pool"
  }
}

Input Schema

Name	Required	Description	Default
`confirm`	No	true only after the user read the statement and said yes
`left_at`	No	the left_at value the dry run returned

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.6.1Nov 14, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the single destructiveHint=false annotation, the description discloses the key behaviors: the first call signs nothing and only shows a statement; confirm=true signs the statement with the user's key and writes a leave file the user must open as a pull request; no order is placed and no money moves. It also documents the mainnet requirement and the testnet failure shape ({error, code: testnet}), which annotations do not cover.

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 content is front-loaded with the effect and the two-step flow, and every clause carries operational information. It is dense in a single paragraph, and a sentence or two could be tightened, but little is genuinely wasted.

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?

With no output schema, the description still states what is returned (the statement, then the signed leave file path), covers authentication/key needs, network constraints, and the failure mode. Nothing an agent needs to call it safely appears to be missing.

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 baseline is 3, but the description adds genuine sequencing meaning: confirm must be true only after the user read the statement, and left_at must be the value returned by the first (dry-run) call. That clarifies the coupling between the two parameters and the two-step workflow beyond the field descriptions.

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 and resource ("Leave the research pool") and immediately states the effect on the user's data (address and rows dropped, persists until a later join). It also names the contrasting sibling join_pool and the prerequisite get_pool_status, so an agent can distinguish it 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use and when-not-to-proceed rules: call only when the user asked to leave, check membership first with get_pool_status, and confirm only after the user has read the statement. The two-step dry-run/confirm flow is spelled out with the exact parameter required for the second step.

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