Skip to main content
Glama

Remove image

remove_asset
DestructiveIdempotent

Permanently delete a hosted image — the file and its record. Use it to clear out images the user does not want kept: a wrong crop, an abandoned draft, a photo they asked you to remove. Get the id from get_uploaded_page_assets. An image a published page uses is refused, because deleting it would leave a broken image on the live page; republish that page without it first, or pass force. This cannot be undone.

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": {
      "assetId": "<assetId>"
    },
    "name": "remove_asset"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNoDelete even though a published page uses the image, accepting that the page will show a broken image until it is republished. Only with the user's agreement.
assetIdYesThe asset's id, as returned by get_uploaded_page_assets (the "id" field, also the filename in its URL).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the details that actually matter: irreversibility, and the refusal behavior when a published page references the asset. The force override and the broken-image consequence are both disclosed rather than left to inference.

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?

Four sentences, front-loaded with the destructive action, then sourcing, then the failure mode and override. Minimal waste; the illustrative examples in the second sentence are slightly redundant with each other but earn their place by disambiguating intent.

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 destructive tool with no output schema, the description covers action, id source, precondition failure, override, and irreversibility — everything needed to call it correctly or correctly decline. Nothing material is missing.

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% and both params are already documented, so the baseline is 3. The description still adds value by framing force as the escape hatch for the published-page guard and by pointing at where assetId comes from, though the per-parameter nuance largely lives in the schema rather than the prose.

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?

"Permanently delete a hosted image — the file and its record" gives a precise verb, resource, and scope (both binary and DB record). It is clearly distinct from siblings like upload_asset, discard_draft, and custom_domain_remove, so an agent can route 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?

It enumerates concrete when-to-use cases (wrong crop, abandoned draft, user-requested removal), names the prerequisite source for the id (get_uploaded_page_assets), and gives the blocked path plus remedy (republish without the image, or pass force). When-not and alternative are both explicit.

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.