Skip to main content
Glama

ExducerAI GPU cloud

Book GPUs

create_booking
Idempotent

Send a GPU request. It is created as requested or queued and becomes running later (use wait_for_deployment); nothing is charged before it runs, then credit is drawn per minute. Quote first with quote_booking and get the user's yes on the total. Retry-safe: see idempotency_key.

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": {
      "server_id": "<server_id>",
      "gpus": "<gpus>",
      "hours": "<hours>",
      "confirm": "<confirm>"
    },
    "name": "create_booking"
  }
}

Input Schema

NameRequiredDescriptionDefault
gpusYesNumber of GPUs: one of the server's allowed_gpu_counts.
hoursYesDuration in hours. A live booking has a minimum (the API answers duration_below_minimum under it).
imageNoA container image instead of a template. Only images the platform already runs are accepted.
notesNoA note for the staff who place the request.
confirmYesMust be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely.
templateNoTemplate slug from list_templates. Left out: the default PyTorch image.
server_idYesServer id from list_servers.
auto_renewNoRenew by itself at the end of the term while credit lasts.
renew_hoursNoThe renewal block in hours.
sandbox_speedNoSandbox keys only: shorten every simulated wait this many times.
ssh_public_keyNoThe text of the user's SSH public key (.pub), one key per line. Left out, the keys saved on the account are used. Required with a sandbox key.
idempotency_keyNoOptional. 8 to 128 characters. Reuse the same value when retrying the same request. Left out, one is derived from the request and the UTC date, so the identical request the same day returns the first answer; pass a new value to really do it a second time.
client_referenceNoYour own reference for this deployment; unique among the account's live deployments.
sandbox_scenarioNoSandbox keys only: the lifecycle to simulate.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (idempotentHint, destructiveHint), the description discloses the charge model (nothing before it runs, credit drawn per minute), the queuing behavior, and the retry-safety contract. This is exactly the financial/concurrency context structured fields do not carry.

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?

Three short sentences, front-loaded with the action and outcome, then prerequisites, then the idempotency pointer. Dense and waste-free, though the mid-sentence clause about queuing and charging is slightly packed and could read more cleanly.

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?

For a 14-parameter mutating booking tool with no output schema, the description covers the lifecycle, billing, prerequisite quoting, and retry semantics well. It stops short of saying what the call returns (a deployment handle, presumably) and how a queued versus immediate result is distinguishable, which would help an agent act on the response.

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%, so every one of the 14 parameters, including idempotency_key, confirm, and sandbox_scenario, is already documented in the schema. The description's pointer to idempotency_key and its hint that the user must approve the total reinforce confirm but add little syntax or format knowledge beyond the schema; 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?

"Send a GPU request" gives a specific verb and resource, then immediately states the outcome space (created as requested or queued, running later), which separates it cleanly from quote_booking and wait_for_deployment.

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?

Explicitly routes the agent: quote first with quote_booking, obtain the user's yes on the total, then use wait_for_deployment after the request. It states both the prerequisite sequence and the follow-up alternative, leaving nothing to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources