Skip to main content
Glama

generate_picture

Create a character, object, or background picture from plain words using Higgsfield credits, with a price confirmation step and optional placement into a shot or the Media bin.

Instructions

Make any picture with Higgsfield (Nano Banana) from words: a character or object (its background is taken off) or a background. Spends the person's Higgsfield credits: the first call (without confirm) only returns the price and credits left; ask the person, then call again with the same arguments and confirm: true. Waits up to about 50 s; if it isn't done, call picture_status. put defaults to media (the Media bin). Use the shortcuts generate_character (straight into a shot's cast) or generate_place (straight in as the shot's background) when that's what you want. For a free drawing in the style itself, use draw_character, draw_object or draw_place.

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": {
      "kind": "<kind>",
      "prompt": "<prompt>"
    },
    "name": "generate_picture"
  }
}

Input Schema

NameRequiredDescriptionDefault
putNoWhere it goes: shot (into the shot), media (the project's Media bin), none (only the generated pictures list).
kindYescharacter or object (background taken off), or background (a place, no people).
nameNoA short name for it in the project.
shotNoShot id (from get_project). Default: the shot on screen.
promptYesWhat to draw, in plain words. @1, @2 point at the reference pictures in order.
confirmNotrue only after the person agreed to the price.
qualityNoDefault 2k. About 1.5 / 2 / 3 Higgsfield credits.
replaceNoA cast member id in that shot whose picture this replaces.
referencesNoPaths of up to 4 pictures on this computer to keep the same person or thing.
from_picturesNoIds of pictures made before (generated_pictures) to use as references.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.2
    • addedInput schema / properties / kind / description
      Added value: +"character or object (background taken off), or background (a place, no people)."
    • addedInput schema / properties / put / description
      Added value: +"Where it goes: shot (into the shot), media (the project's Media bin), none (only the generated pictures list)."
    • changedInput schema / properties / quality / description
      Previous value: -"Default 2k."New value: +"Default 2k. About 1.5 / 2 / 3 Higgsfield credits."
  2. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false, idempotentHint=false), it discloses the credit cost model, the mandatory two-phase confirm protocol, the ~50 s wait, and the polling fallback. These are the critical behaviors an agent could not infer from the structured fields.

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 purpose, then cost/confirm behavior, then alternatives — a sensible ordering with no filler sentences. It is a single dense block, and the parenthetical "(Nano Banana)" and repeated phrasing add minor clutter, but every sentence carries information.

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 10-parameter, non-idempotent, credit-spending generation tool with no output schema, the description covers cost, confirmation, latency, fallback, and destination defaults. An agent has everything needed to call it correctly and to avoid burning credits by accident.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description goes further by explaining the confirm/dry-run semantics and the default value of put (media). It does not restate quality tiers, references, or replace, leaving those entirely to the schema.

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?

The description opens with a specific verb and resource ("Make any picture with Higgsfield") and immediately enumerates the output kinds — character/object with background removed, or a background. It is distinguishable from generate_character, generate_place, and the draw_* family 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?

It names explicit alternatives and the conditions selecting them: generate_character for a shot's cast, generate_place for a shot's background, and draw_character/draw_object/draw_place for a free drawing in the style. It also routes to picture_status if the call hasn't finished.

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