Nodehour: GPU capacity sized from your run and quoted by providers

Send the requirement

send_requirement

Idempotent

Send the requirement to Nodehour once the buyer says to: the first send records the request (its receipt token is the requirement's token, for request_status and offers); a later send of a changed requirement records a revision of the same request. Name the revision the buyer saw. This orders nothing: an offer comes later and is accepted separately on its exact terms.

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": {
      "id": "<id>",
      "token": "<token>",
      "revision": "<revision>"
    },
    "name": "send_requirement"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	The requirement id from an earlier answer
`op_id`	No
`token`	Yes	Its private token (also the receipt token of the request it is sent as); keep it private
`action`	No	What the buyer wants done (default quote): to buy, lease, verify...
`contact`	No
`revision`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4/5.0

Behavior5/5

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

Annotations already mark it as a non-readonly, idempotent, non-destructive mutation. The description adds substantial lifecycle detail: the first send records the request, a later changed send records a revision, the receipt token links to request_status and offers, and sending does not create an order.

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 description is front-loaded with the send action, and each sentence carries distinct information about recording, revision, and non-ordering. It is dense but not repetitive, though the first sentence is long and slightly run-on.

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

Completeness3/5

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

It covers the core send lifecycle and boundary conditions for a mutation tool with no output schema. It still leaves op_id and contact semantics unexplained and does not fully clarify repeated-send behavior, so it is adequate but incomplete.

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?

The schema documents id, token, and action, while the description adds critical meaning for revision ('Name the revision the buyer saw') and reinforces that the token is the receipt token. However op_id and the contact object remain undocumented, and schema coverage is only 50%.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource ('Send the requirement to Nodehour') and explains that the first send records a request while a later changed send records a revision. It does not explicitly distinguish this from sibling submit_request, so it is clear but not fully differentiated from alternatives.

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 sets a precondition ('once the buyer says to') and a clear boundary ('This orders nothing'; the offer is accepted separately). It does not name edit_requirement or submit_request as alternatives, so routing among siblings remains implicit.

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

All Nodehour: GPU capacity sized from your run and quoted by providers tools Inspect

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

Need Help?