Skip to main content
Glama

put_picture

Place a previously generated picture into your project as a character, object, background, or media item, optionally replacing a cast member's picture. Returns where it landed.

Instructions

Put a picture made before (an id from generated_pictures) into the project, free: as a character or object (joins a shot's cast, or replaces a member's picture), a background (the shot's place) or media (the Media bin). One undo step. Returns where it went. For a file on this computer use upload; for a new picture use generate_*.

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>",
      "as": "<as>"
    },
    "name": "put_picture"
  }
}

Input Schema

NameRequiredDescriptionDefault
asYesHow it goes into the project.
idYesA picture id from generated_pictures.
nameNoA short name for it in the project.
shotNoShot id (from get_project). Default: the shot on screen.
replaceNoA cast member id in that shot whose picture this replaces.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.2
    • addedInput schema / properties / as / description
      Added value: +"How it goes into the project."
    • addedInput schema / properties / id / description
      Added value: +"A picture id from generated_pictures."
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare non-read-only, non-idempotent, non-destructive, but the description adds traits annotations cannot express: the operation is free (no credit cost), it consumes exactly one undo step, and it reports back where the picture landed. That the 'replaces a member's picture' branch is recoverable via one undo reconciles the replace semantics with destructiveHint=false. It stops short of describing failure modes or what happens if the shot id is stale.

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 core action, then the placement variants, then side effects, then alternatives — a sensible order with no filler sentences. It is dense and somewhat telegraphic ('free:', 'One undo step.'), which suits a tool description but costs a little readability.

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 five-parameter mutation with no output schema, the description covers prerequisites, placement modes, cost, undo scope, and the fact that a location is returned, plus sibling routing. The only residual gap is that the shape of the returned location is not described, though it is minimal for a 'where did it go' result.

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, but the description adds real meaning by mapping each `as` value to a project effect (joins a shot's cast, replaces a member's picture, sets the shot's place, lands in the Media bin) and by clarifying that `shot` defaults to the shot on screen. That relationship between `replace` and `character` is inferable from the description in a way the schema alone does not spell out.

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?

States a specific verb and resource ('Put a picture ... into the project') and immediately enumerates the four distinct outcomes via the `as` values: cast member, background, or Media bin. It also names the sibling it is not ('For a file on this computer use upload; for a new picture use generate_*'), so an agent can route correctly without opening a 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 separates three cases: reuse an existing generated picture (this tool), ingest a local file (upload), or create a new picture (generate_*). The prerequisite that the id must come from generated_pictures is stated inline, which is exactly the condition an agent needs to check before calling.

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