Skip to main content
Glama

Delete Images

delete_images
DestructiveIdempotent

Delete one or more existing image assets that the user can access, including Brand Library images. Use image IDs, not selected-model generation-job IDs.

The images stop appearing in image list, search, and read results. Re-deleting an already-deleted image is a no-op.

Only call this when the user has explicitly asked to delete specific images. For bulk cleanup, first list the candidates with list_images and confirm the exact set with the user.

deleted_count may be lower than the number of IDs passed: images the user cannot delete, or that were already deleted, are skipped rather than erroring.

Args:

  • image_ids: Image IDs to delete, from list_images or generation outputs' media IDs. Do not pass the job IDs returned by generate_image.

Returns: { "deleted_count": number, "message_for_assistant"?: string }

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": {
      "image_ids": "<image_ids>"
    },
    "name": "delete_images"
  }
}

Input Schema

NameRequiredDescriptionDefault
image_idsYesIDs of the image assets the user asked to delete. Take them from list_images or generation outputs' media IDs. Generation-job IDs returned by generate_image cannot identify images for deletion.
llm_modelNoThe model identifier you are running as, for example "claude-opus-4-8" or "gpt-5.2". Omit it or pass "unknown" if you are not certain; the tool runs the same either way. Recorded only for the server developer's analytics.

Output Schema

NameRequiredDescriptionDefault
deleted_countYesNumber of images deleted. Skipped IDs are not counted.
message_for_assistantNoContext, explanations, or actionable guidance for the calling assistant. Hosts may display it, but it is not copy that must be shown to the user verbatim.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare destructive/idempotent, and the description still adds substantial context beyond them: images disappear from list, search, and read results; re-deletion is a no-op; and most importantly, deleted_count may be lower than the IDs passed because unauthorized or already-deleted images are silently skipped rather than erroring. That partial-success semantics is exactly the kind of trait annotations cannot express.

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?

Well front-loaded: purpose first, then effects, then usage gating, then semantics. Minor waste in the trailing 'Args' and 'Returns' blocks that duplicate the input schema and the existing output schema.

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 destructive, two-parameter tool with an output schema, everything an agent needs is covered: identifier sourcing, user-confirmation requirement, post-deletion visibility, idempotency, and partial-failure behavior. The return shape needn't be explained further because an output schema exists.

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% and the Args section largely restates what the schema descriptions already say (image IDs from list_images or generation media IDs, not job IDs). The description adds little new meaning beyond the structured field text and does not mention the llm_model parameter at all, so baseline 3 applies.

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 ('Delete one or more existing image assets... including Brand Library images') and immediately disambiguates the identifier type from generate_image's generation-job IDs. An agent can tell exactly what this tool operates on 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?

Explicit gating is given: 'Only call this when the user has explicitly asked to delete specific images,' plus a concrete alternative workflow for bulk cleanup — list with list_images, then confirm the exact set with the user. When-to-use and when-to-do-something-else are both stated.

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