---
title: "Source: schemas/answer_budgets.json"
description: "Generated page for the indexed contract source schemas/answer_budgets.json: its schema fields or contract text, and its published text."
slug: /reference/sources/schemas/answer-budgets
order: 8
visibility: public
redirects_from: []
---

# Source: schemas/answer\_budgets\.json

Generated automatically from the [published contract sources](/cloud/reference/about/#contract-sources).

Source path: schemas/answer\_budgets\.json.

## Complete source

```json
{
  "title": "tzCloud — tool-answer budgets",
  "description": "The most prose each form of a tool answer may hold, one row per form. Every budget counts Unicode code points over the composed text and bounds the answer's fixed words. A list of the caller's own names or identifiers counts at one entry, and so does one such value.",
  "version": "2026-11-20.1",
  "budgets": [
    {
      "form": "completed.detail",
      "budget": 600,
      "description": "The detail of a completed answer: what happened and what to do next."
    },
    {
      "form": "completed.summary",
      "budget": 700,
      "description": "The summary of a completed answer, read as its headline."
    },
    {
      "form": "outcome.detail",
      "budget": 600,
      "description": "The detail of a version's outcome, as read_status and list_versions answer it."
    },
    {
      "form": "pending.detail",
      "budget": 300,
      "description": "The detail of a pending answer, which says the action waits for the person's approval in the browser."
    },
    {
      "form": "pending.description",
      "budget": 400,
      "description": "The description of a pending answer: what the action does once the person approves it."
    },
    {
      "form": "refusal.detail",
      "budget": 400,
      "description": "The detail of a refusal: what was refused and why."
    },
    {
      "form": "row.note",
      "budget": 200,
      "description": "The note an answer carries, on one row of a list or at the answer's top level."
    },
    {
      "form": "environment.grain_note",
      "budget": 200,
      "description": "The note on each environment in read_status's answer, saying how that environment runs."
    },
    {
      "form": "read.continuation",
      "budget": 570,
      "description": "The continuation of a text read that holds less than the whole text: the characters read and how to read on."
    },
    {
      "form": "mcp.second_block",
      "budget": 900,
      "description": "The second content block of an MCP tool result, after the answer itself."
    }
  ]
}

```
