Skip to main content
Glama

Edit a thumbnail with an instruction

edit_thumbnail
Idempotent

Change one option's thumbnail with a plain instruction, for example "make the background darker". An image-edit model applies it to the current version; on Editable runs it changes only the background, never the text. Adds a new version; nothing is lost. Consumes edit allowance. Use only at the user's request, with one idempotencyKey per intended edit. Poll get_thumbnail.

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": {
      "runId": "<runId>",
      "rank": "<rank>",
      "idempotencyKey": "<idempotencyKey>",
      "instruction": "<instruction>"
    },
    "name": "edit_thumbnail"
  }
}

Input Schema

NameRequiredDescriptionDefault
rankYes
runIdYes
instructionYes
idempotencyKeyYes

Output Schema

NameRequiredDescriptionDefault
rankYes
runIdYes
editIdYes
statusYes
pollAfterSecondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Goes well past the annotations: it discloses that a new version is created and nothing is lost (non-destructive in practice, consistent with destructiveHint=false), that the call consumes a metered "edit allowance," and that platform rules limit changes to the background on Editable runs. Missing only auth/prerequisite detail and what a failed or rejected edit does to the allowance.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five short sentences, each carrying distinct, actionable information: the action, the model's scope, reversibility, cost, invocation constraint, and the polling next step. Front-loaded with the purpose and free of hedging or restatement of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Strong on cost, reversibility, idempotency, and next step, and an output schema exists so return values need no explanation. However, for a four-required-parameter mutation tool with zero schema descriptions, omitting any explanation of runId and rank leaves a real gap an agent could fill incorrectly.

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

Parameters2/5

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

Schema description coverage is 0% across four required parameters, so the description carries the full burden. It explains instruction (with an example phrasing) and idempotencyKey semantics, but says nothing at all about runId or rank — an agent gets no hint that rank is an option index bounded 1–24 or which run the edit targets.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Change one option's thumbnail with a plain instruction") and scopes the effect ("on Editable runs it changes only the background, never the text"), which behaviorally separates it from a layer-level edit. It never names the sibling tools it differs from, so an agent must infer the boundary rather than being routed explicitly.

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?

Gives a clear gating condition — "Use only at the user's request" — and a required calling discipline (one idempotencyKey per intended edit), plus the follow-up action "Poll get_thumbnail." It stops short of stating when to prefer edit_thumbnail_layers or restore_thumbnail_version instead, so alternatives remain unaddressed.

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