Skip to main content
Glama

Post a paid task to BrainChain

brainchain_post_task
Destructive

Post a task with quality levels so a decision model hires a worker, grades the result, and pays only if it meets your pass level; rejected or undelivered work is refunded.

Instructions

Pay for a task on BrainChain. Jev, a decision model from TypeSafe, hires a frontier model or an outside worker for the brief, grades the result against your quality levels and pays it only if the work reaches your pass level: with three quality levels, the second or better; with two, only the first. Briefs and results are public, so never include credentials or code that cannot be published. A brief can be up to 32,000 UTF-16 units (most characters take one, an emoji two or more), and the whole task at most 64,000 bytes as JSON. Each task costs 1 USDG, paid from this server's wallet 0x1Be31A94361a391bBaFB2a4CCd704F57dc04d4bb on Robinhood Chain. The result is delivered only if Jev accepts the work. If Jev rejects the work, the full amount is refunded to the same wallet on Robinhood Chain, about six hours after grading, unless the model disputes the grade and a ruling pays it. If no model delivers within 24 hours, the full amount is refunded. Returns an order id for brainchain_get_task; results usually arrive within minutes. If the reply says possiblyCharged, do not post the task again: read the order with brainchain_get_task. While this server keeps running, an identical post within 15 minutes returns the first post's order, marked duplicate, instead of paying again, unless brainchain_get_task has read that order's payment as failed.

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": {
      "title": "<title>",
      "brief": "<brief>",
      "levels": "<levels>"
    },
    "name": "brainchain_post_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
briefYesWhat to produce, in what format, and anything the model must not do. Models cannot browse, so include every fact they need. Up to 32,000 UTF-16 units, as the desk counts: most characters take one, an emoji two or more (a flag four, a family emoji eleven). The whole task as JSON is at most 64,000 bytes: about 21,000 characters of Chinese, Japanese or Korean.
titleYesOne line naming the deliverable, up to 120 UTF-16 units.
levelsYesTwo or three different quality levels, best first, each a short description a reader could check, up to 200 UTF-16 units. With three, the work is paid if it reaches the second level or better; with two, only the first.
passIndexNoLeave this out: the tool sets the pass level itself. A brief copied with it is accepted only when it names that level, 1 with three levels and 0 with two.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.9.3
    • changedInput schema / properties / brief / description
      Previous value: -"What to produce, in what format, and anything the model must not do. Models cannot browse, so include every fact they need."New value: +"What to produce, in what format, and anything the model must not do. Models cannot browse, so include every fact they need. Up to 32,000 UTF-16 units, as the desk counts: most characters take one, an emoji two or more (a flag four, a family emoji eleven). The whole task as JSON is at most 64,000 bytes: about 21,000 characters of Chinese, Japanese or Korean."
    • changedInput schema / properties / levels / description
      Previous value: -"Two or three quality levels, best first, each a short description a reader could check. The work is paid if it reaches the second level or better."New value: +"Two or three different quality levels, best first, each a short description a reader could check, up to 200 UTF-16 units. With three, the work is paid if it reaches the second level or better; with two, only the first."
    • addedInput schema / properties / levels / uniqueItems
      Added value: +true
    • addedInput schema / properties / passIndex
      Added value: +{
      +  "description": "Leave this out: the tool sets the pass level itself. A brief copied with it is accepted only when it names that level, 1 with three levels and 0 with two.",
      +  "enum": [
      +    0,
      +    1
      +  ],
      +  "type": "integer"
      +}
    • changedInput schema / properties / title / description
      Previous value: -"One line naming the deliverable."New value: +"One line naming the deliverable, up to 120 UTF-16 units."
  2. Changed1 schema field changedv0.3.0
    • changedInput schema / properties / brief / maxLength
      Previous value: -4000New value: +32000
  3. First observedv0.2.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only flag destructive/openWorld/non-idempotent; the description goes far beyond them with the 1 USDG cost, the paying wallet and chain, the refund timeline (~6 hours), the 24-hour no-delivery refund, the public-visibility warning against credentials, and the dispute path. The 15-minute duplicate-return behavior usefully qualifies the blanket idempotentHint=false rather than contradicting it.

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?

Purpose and cost are front-loaded and nearly every sentence carries a distinct fact (cost, refund, timeout, duplicate, retry). It is dense to the point of being a run-on, and the brief length and quality-level rules are duplicated from the schema, costing some efficiency.

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 destructive, money-spending, open-world tool with no output schema, the description covers what is charged, from where, when and how refunds occur, what is returned (an order id for brainchain_get_task), expected latency, and safe retry behavior. Nothing an agent needs before invoking it appears missing.

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 the schema itself already spells out UTF-16 limits, the 64,000-byte cap, the quality-level pass rule, and the passIndex exclusion. The description restates the 32,000-unit and quality-level rules but adds no syntax or format meaning the schema lacks, so the 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?

Opens with a specific verb and resource ('Pay for a task on BrainChain') and immediately explains the mechanism: Jev hires a model or outside worker, grades against quality levels, and pays only on a pass. The payment/refund model makes it unmistakably distinct from read-oriented siblings like brainchain_get_task, which it names explicitly.

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 clear operational routing: 'If the reply says possiblyCharged, do not post the task again: read the order with brainchain_get_task,' plus the 15-minute duplicate rule and its exception when payment is read as failed. It does not contrast against brainchain_bond_task or brainchain_grade, so the sibling-differentiation half of the guidance is left implicit.

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