Skip to main content
Glama

GetBody

Request a robot lease

request_lease

Request a time-boxed rental of an available robot. Select an offered access_type or omit it for the primary rental arrangement. Personnel-operated and equipment-only rentals require empty granted_permissions and mint no control token. Remote controls require configured integration and permitted scope; remote_teleoperation uses supervisory (command) mode unless you pass control_mode teleop and the listing offers it. The window must fit the listing rental_availability; for on_request listings, inquire first and pass the promise_id of an accepted window. The request waits for operator approval (REQUESTED); poll get_lease, then activate once CONFIRMED.

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": {
      "listing_id": "<listing_id>",
      "window_start": "<window_start>",
      "window_end": "<window_end>",
      "granted_permissions": "<granted_permissions>"
    },
    "name": "request_lease"
  }
}

Input Schema

NameRequiredDescriptionDefault
currencyNoPayments are not enabled yet: must be null or omitted.
body_kindNoWhich of the listing's bodies to lease; required when it offers both.
listing_idYes
promise_idNoRedeem a promise of lease (from accept_inquiry): the window must lie within the promised window.
window_endYesISO 8601 datetime, after window_start.
access_typeNo
agreed_priceNoPayment isn't handled through the API (pricing and payouts: hello@getbody.md): must be null or omitted (else 400 payment_arranged_by_getbody).
control_modeNo
window_startYesISO 8601 datetime.
granted_permissionsYesSubset of the listing's permissions_offered.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / access_type
      Added value: +{
      +  "enum": [
      +    "onsite_operator",
      +    "remote_teleoperation",
      +    "equipment_only"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / body_kind / enum
      Previous value: -[
      -  "real",
      -  "simulated"
      -]New value: +[
      +  "real"
      +]
    • addedInput schema / properties / control_mode
      Added value: +{
      +  "enum": [
      +    "supervisory",
      +    "teleop",
      +    "onsite_operator",
      +    "equipment_only"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / promise_id
      Added value: +{
      +  "description": "Redeem a promise of lease (from accept_inquiry): the window must lie within the promised window.",
      +  "type": "integer"
      +}
  2. Changed2 schema fields changed
    • removedInput schema / properties / control_mode
      Removed value: -{
      -  "default": "supervisory",
      -  "enum": [
      -    "supervisory",
      -    "teleop"
      -  ],
      -  "type": "string"
      -}
    • removedInput schema / properties / promise_id
      Removed value: -{
      -  "description": "Redeem a promise of lease (from accept_inquiry): the window must lie within the promised window.",
      -  "type": "integer"
      -}
  3. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only declare write/non-destructive/open-world/non-idempotent; the description adds far more: the request is asynchronous and blocks on operator approval (REQUESTED), some access types mint no control token, and permissions/scope prerequisites gate remote control. The only notable gap for a non-idempotent mutation is that it never addresses duplicate-request behavior or the cost of submitting the same window twice.

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 the action, then progressive detail on access types, preconditions, and the follow-up state machine. Every sentence carries information, though the remote_teleoperation/control_mode sentence is dense enough to require a second read.

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 10-parameter, no-output-schema mutation with an approval state machine, this covers preconditions, defaults, workflow, and follow-up tools. It stops short of saying what a successful call returns (e.g., a lease identifier to poll with), which is the one thing an agent must infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Goes well beyond the 70%-covered schema: it defines the default when access_type is omitted, ties granted_permissions emptiness to personnel-operated/equipment-only rentals, explains that control_mode defaults to supervisory and teleop only works if the listing offers it, and constrains promise_id's window to the promised window. Payment parameters are correctly framed as inert.

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 precise verb+resource+scope: 'Request a time-boxed rental of an available robot.' An agent can immediately distinguish this from get_lease (read state), activate_lease (start), cancel_lease, and create_inquiry (pre-lease negotiation) without opening any 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?

Explicitly routes the agent through the workflow: inquire first for on_request listings and pass promise_id, poll get_lease while REQUESTED, then activate once CONFIRMED. It also gives the selection rule between access types ('omit it for the primary rental arrangement') and conditions that disqualify a remote request (integration and permitted scope required).

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