Skip to main content
Glama

Change the text in an image

replace_text

Change or remove text in a photo or screenshot and keep the same font, colour and background. Give each line to change as { from, to }: "from" is the text as it appears in the image, "to" the new text (empty to remove it). Up to 20 lines per image; 1 credit per image. The image is scanned first; if a "from" is not found, nothing is charged and the error lists the lines that were read. IDs, certificates, receipts, invoices and bank documents are refused. Edits usually take about a minute; waits up to 50 seconds, and if still editing, call get_edit with wait_seconds 30.

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": {
      "replacements": "<replacements>"
    },
    "name": "replace_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
hintNoOptional: where the text is when it appears more than once, e.g. "the line at the bottom".
localeNoLanguage of the person asking (for our statistics only). Default en.
image_urlNoPublic https URL of the image (PNG or JPG).
image_base64NoThe image as base64, with or without a data: prefix. Use when there is no URL.
replacementsYes
wait_secondsNoHow long to wait for the result before returning, 0 to 50 seconds.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / locale / enum
      Previous value: -[
      -  "en",
      -  "es",
      -  "ja",
      -  "zh-Hans",
      -  "zh-Hant",
      -  "ko",
      -  "ar",
      -  "fr"
      -]New value: +[
      +  "en",
      +  "es",
      +  "ja",
      +  "zh-Hans",
      +  "zh-Hant",
      +  "ko",
      +  "ar",
      +  "fr",
      +  "id"
      +]
  2. Changed1 schema field changed
    • changedInput schema / properties / locale / enum
      Previous value: -[
      -  "en",
      -  "es",
      -  "ja",
      -  "zh-Hans",
      -  "zh-Hant",
      -  "ko",
      -  "ar"
      -]New value: +[
      +  "en",
      +  "es",
      +  "ja",
      +  "zh-Hans",
      +  "zh-Hant",
      +  "ko",
      +  "ar",
      +  "fr"
      +]
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false, openWorldHint=true, destructiveHint=false; the description adds substantial context beyond that: 1 credit per image, no charge when a 'from' string is not found, the error lists lines actually read, ~1 minute typical runtime, and a 50-second wait cap with get_edit polling. It does not describe what a successful response contains (e.g. an edit ID), which is the main remaining gap.

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 cost, validation, refusals, and timing in a logical order. Dense but nearly every clause carries operational information; the final timing/polling sentence is slightly run-on but still earns its place.

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?

With no output schema, the description covers failure behavior, cost, and the async polling path, which is what an agent needs to call and follow up correctly. It stops short of describing the success payload shape, a minor gap for a tool that returns an edit handle.

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 already 83%, so the baseline is 3, but the description adds real meaning: the {from, to} pair semantics, that an empty 'to' removes the line, and the 20-line cap. It omits the 'hint' and 'locale' parameters, which the schema covers, so it does not fully compensate but clearly exceeds baseline.

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 ('Change or remove text in a photo or screenshot') and immediately distinguishes itself from scan_text and get_edit by describing the edit-and-preserve-styling behavior. An agent can tell what this does without opening the 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?

Gives explicit when-to-use context (editing text in images), when-not (IDs, certificates, receipts, invoices, bank documents are refused), and names the follow-up alternative get_edit with a concrete wait_seconds value. The polling path is spelled out rather than left to inference.

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