Skip to main content
Glama

Precise edit (Ideogram 4.5)

ideogram_precise_edit

Edit an image while keeping untouched pixels exactly as they are: apply a prompt, optional black-mask region, reference images, and a context window to guide changes.

Instructions

Edit an image with Ideogram 4.5 at its exact size: pixels the edit does not change stay as they are. Takes the image, an optional mask (black = edit), up to 4 reference images that guide the edit, and context_window to confine it. Results are saved to the output directory; ideogram_quote prices a call first (nothing is generated).

Input Schema

NameRequiredDescriptionDefault
maskNoLocal mask image file or a public https URL, the same size as the source
seedNoRandom seed for a reproducible result
imageNoLocal image file to work on, or a public https URL of one
modelNoThe model (default ideogram-4-5); each takes the fields of its variant below
promptNoWhat to create or change, in natural language
wait_sNoSeconds to wait for the result (0-50, default 45). The job is accepted first; if it is still running when the wait ends, the result is its generation_id for ideogram_generation (never resubmitted, never billed twice).
privateNoKeep the result out of Ideogram's public feed; true unless you set false (enterprise accounts are always private)
qualityNovery_low, low, medium or high: higher costs more
num_imagesNoHow many images to make (each is billed)
inline_imagesNotrue: each saved image is also returned as image content (base64; one over 3.75 MB, or past 10 MB in total, by path only), for a client without file access
context_windowNoWhere to edit: "none" (whole image, default), "auto" (around the mask) or "y_min,x_min,y_max,x_max"
reference_imagesNoLocal image files (or public https URLs) that guide the edit (never edited themselves); at most 4, at most 3 with a mask
image_asset_identifierNoAn Ideogram asset (an upload or an earlier result) instead of a local image
enable_copyright_detectionNoRun Ideogram's copyright detection on the result (adds latency)
reference_image_asset_identifiersNoIdeogram assets that guide the edit; needs the edited image by reference too, not with a mask

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.5.0

TDQS

A4.3/5.0
Behavior4/5

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

No annotations are provided, so the description carries full burden; it does disclose key behavior: results are saved to the output directory, nothing is generated by the quote, mask semantics (black = edit), reference images are not themselves edited, and a max of 4 (3 with mask). It does not disclose billing/rate behavior or failure modes, but covers the important operational traits.

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?

Two dense sentences, front-loaded with the core distinguishing trait (exact size, unchanged pixels preserved) before enumerating inputs and the sibling quote tool. No filler, though the second sentence is a heavy clause stack.

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 15-parameter generation tool with no output schema and no annotations, the description gives the essentials an agent needs: input roles (image, mask, reference images, context_window), what changes and what doesn't, and the pricing sibling. Missing details on output format and billing, but the schema descriptions cover most parameters.

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 description coverage is 100%, so the schema already carries parameter meaning. The description reinforces the most error-prone semantics: mask color convention, context_window purpose, reference-image count limits, and the image+mask condition. It does not add meaning beyond schema for most parameters, keeping it near the 100%-coverage baseline, but the reinforced constraints add real value.

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+resource (edit an image with Ideogram 4.5) and defines the distinguishing scope: pixels not changed stay as they are, at the exact size. Among many image-editing siblings (ideogram_edit, ideogram_inpaint, ideogram_remove_object), the 'exact size, unchanged pixels preserved' framing differentiates it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains the conceptual model of the operation (black = edit in mask, context_window confines the edit, reference images guide but are never edited) which implies when this tool is right. It names ideogram_quote as the pricing alternative, but does not explicitly exclude the many overlapping edit siblings (inpaint, remove_object, replace_background), so routing is only partly disambiguated.

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