Skip to main content
Glama

CarlNotes

Change a topic's image

set_topic_image
Destructive

Change the image of a CarlNotes topic you may edit to the public jpeg, png, or webp at image_url. The previous image is deleted. Carl renders a new image only from the topic page, so to regenerate the image, send the user to the topic page. Use it when the user asks Carl or CarlNotes to change a topic's image, with phrases like change the topic image, regenerate the image, or use this picture.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "set_topic_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
topic_idNoThe topic's id. Optional on a topic-bound server, which already knows its topic.
image_urlNoA public jpeg, png, or webp to use as the topic's image.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • removedInput schema / properties / image_prompt
      Removed value: -{
      -  "description": "What the regenerated image shows. Leave it out to regenerate from the topic itself.",
      -  "maxLength": 500,
      -  "minLength": 1,
      -  "type": "string"
      -}
    • changedInput schema / properties / image_url / description
      Previous value: -"A public jpeg, png, or webp to use as the image. Leave it out to regenerate the image."New value: +"A public jpeg, png, or webp to use as the topic's image."
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations it discloses consequences and constraints the agent could not otherwise know: 'The previous image is deleted' (concretizing destructiveHint), the 'topic you may edit' permission requirement, and the non-obvious regeneration quirk that Carl only renders a new image from the topic page, so the agent must redirect the user there. That last point in particular prevents a wrong-action attempt.

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?

It is front-loaded with the action and the constraint in the opening sentence, then adds usage cues. There is mild redundancy: 'regenerate the image' appears both as a task phrase in the description body and again in the trigger list, and the format list duplicates the schema. Overall it is dense and earns most of its space.

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 two-parameter mutation with no output schema, the description covers purpose, permissions, destructive side effect, input constraints, invocation triggers, and the important post-action caveat about regenerating from the topic page. Nothing an agent needs in order to call it correctly or explain the result to a user is missing.

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

Parameters3/5

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

Schema coverage is 100%, so both parameters are already documented, including topic_id being optional on a topic-bound server. The description mostly restates the accepted image formats already present in the image_url schema description, adding no new syntax, sizing, or fallback detail. Baseline 3 applies when the schema carries the parameter burden.

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 first sentence states a specific verb and resource ('Change the image of a CarlNotes topic') and names the exact input ('the public jpeg, png, or webp at image_url'). It is clearly distinguishable from siblings such as edit_topic (metadata edits) and add_topic_attachment (attachments).

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?

Usage is stated explicitly with trigger phrases: 'Use it when the user asks Carl or CarlNotes to change a topic's image, with phrases like change the topic image, regenerate the image, or use this picture.' That gives an agent concrete invocation cues. It stops short of naming a when-not condition or a competing tool, so it is strong but not complete routing guidance.

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.