Skip to main content
Glama
Sign In

Blackwood State

by io.github.Blackwood-State
OverviewDiscussionsAdmin

Image generation

blackwood_image_generate
Read-onlyIdempotent

Use when you need image generation, an AI image generator or text to image from a prompt for illustrations, mockups or social posts. Do not use for image edits, specific sizes, photos of real people or more than one image per call. Returns JSON with an AI-generated image from a text prompt: a 1024x1024 JPEG made by FLUX.1 schnell on Workers AI, as base64 for 0.03 USDC per call. Result in the same call (about 10000 ms); a status tool polls for free if it takes longer. Category: Media.

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": {
      "prompt": "<prompt>"
    },
    "name": "blackwood_image_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsNoDiffusion steps (1-8, 4 when omitted); more steps, more detail
promptYesWhat the image should show, in English, e.g. a lighthouse on a cliff at sunset, watercolor
response_formatNoconcise (the default when omitted) keeps the JSON short: long fields such as base64 images or audio come back as separate image/audio content blocks and other long strings are cut with a marker; detailed returns the full JSON

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / anyOf
      Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "done": {
-        "type": "boolean"
-      },
-      "error": {
-        "additionalProperties": false,
-        "properties": {
-          "message": {
-            "type": "string"
-          },
-          "name": {
-            "type": "string"
-          }
-        },
-        "required": [
-          "name",
-          "message"
-        ],
-        "type": "object"
-      },
-      "jobId": {
-        "type": "string"
-      },
-      "output": {
-        "additionalProperties": false,
-        "properties": {
-          "imageBase64": {
-            "type": "string"
-          },
-          "mimeType": {
-            "const": "image/jpeg",
-            "type": "string"
-          },
-          "model": {
-            "type": "string"
-          },
-          "prompt": {
-            "type": "string"
-          },
-          "steps": {
-            "maximum": 9007199254740991,
-            "minimum": -9007199254740991,
-            "type": "integer"
-          }
-        },
-        "required": [
-          "model",
-          "prompt",
-          "steps",
-          "mimeType",
-          "imageBase64"
-        ],
-        "type": "object"
-      },
-      "pollUrl": {
-        "type": "string"
-      },
-      "status": {
-        "enum": [
-          "queued",
-          "running",
-          "paused",
-          "errored",
-          "terminated",
-          "complete",
-          "waiting",
-          "waitingForPause",
-          "rollingBack",
-          "unknown"
-        ],
-        "type": "string"
-      }
-    },
-    "required": [
-      "jobId",
-      "status",
-      "done",
-      "pollUrl"
-    ],
-    "type": "object"
-  },
-  {
-    "description": "x402 PaymentRequired (returned with isError when payment is needed)",
-    "properties": {
-      "accepts": {
-        "items": {
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "error": {
-        "type": "string"
-      },
-      "extensions": {
-        "type": "object"
-      },
-      "resource": {
-        "type": "object"
-      },
-      "x402Version": {
-        "type": "integer"
-      }
-    },
-    "required": [
-      "x402Version",
-      "accepts"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "done": {
+        "type": "boolean"
+      },
+      "error": {
+        "additionalProperties": false,
+        "properties": {
+          "message": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "name",
+          "message"
+        ],
+        "type": "object"
+      },
+      "jobId": {
+        "type": "string"
+      },
+      "next": {
+        "additionalProperties": false,
+        "description": "Suggested next paid call in the same family (call it in a loop when the task continues)",
+        "properties": {
+          "method": {
+            "enum": [
+              "GET",
+              "POST"
+            ],
+            "type": "string"
+          },
+          "sample": {
+            "description": "Free fixed sample of the whole family",
+            "type": "string"
+          },
+          "service": {
+            "description": "Service id of the suggested next paid call",
+            "type": "string"
+          },
+          "tool": {
+            "description": "MCP tool name of the same call",
+            "type": "string"
+          },
+          "url": {
+            "description": "Paid route of the next call",
+            "type": "string"
+          },
+          "useWhen": {
+            "description": "When the next call is the right one",
+            "type": "string"
+          }
+        },
+        "required": [
+          "service",
+          "tool",
+          "method",
+          "url",
+          "useWhen",
+          "sample"
+        ],
+        "type": "object"
+      },
+      "output": {
+        "additionalProperties": false,
+        "properties": {
+          "imageBase64": {
+            "type": "string"
+          },
+          "mimeType": {
+            "const": "image/jpeg",
+            "type": "string"
+          },
+          "model": {
+            "type": "string"
+          },
+          "prompt": {
+            "type": "string"
+          },
+          "steps": {
+            "maximum": 9007199254740991,
+            "minimum": -9007199254740991,
+            "type": "integer"
+          }
+        },
+        "required": [
+          "model",
+          "prompt",
+          "steps",
+          "mimeType",
+          "imageBase64"
+        ],
+        "type": "object"
+      },
+      "pollUrl": {
+        "type": "string"
+      },
+      "status": {
+        "enum": [
+          "queued",
+          "running",
+          "paused",
+          "errored",
+          "terminated",
+          "complete",
+          "waiting",
+          "waitingForPause",
+          "rollingBack",
+          "unknown"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "jobId",
+      "status",
+      "done",
+      "pollUrl"
+    ],
+    "type": "object"
+  },
+  {
+    "description": "x402 PaymentRequired (returned with isError when payment is needed)",
+    "properties": {
+      "accepts": {
+        "items": {
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "error": {
+        "type": "string"
+      },
+      "extensions": {
+        "type": "object"
+      },
+      "resource": {
+        "type": "object"
+      },
+      "x402Version": {
+        "type": "integer"
+      }
+    },
+    "required": [
+      "x402Version",
+      "accepts"
+    ],
+    "type": "object"
+  }
+]
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, but the description adds substantial behavior the annotations cannot convey: cost (0.03 USDC per call), expected latency (~10000 ms), the exact model and output (FLUX.1 schnell on Workers AI, 1024x1024 JPEG base64), and the fallback polling path. This is exactly the kind of paid-call, latency, and fallback context an agent needs before invoking.

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 usage condition and exclusion list before the output/cost details, so the reader can decide fast. The synonym chain ("image generation, an AI image generator or text to image") is arguably keyword padding, and the paragraph packs four distinct concerns into one block, which slightly hurts scannability.

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?

Given an existing output schema, the description need not explain return values, yet it still covers model, resolution, format, cost, latency, and the async escape hatch. For a paid, slow, single-image generation tool, an agent has everything required to call it correctly or route elsewhere.

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 each parameter (prompt, steps, response_format) already carries its own description, so the baseline of 3 applies. The description adds only marginal parameter-adjacent meaning: that output size is fixed ("Do not use for specific sizes") and that generation is one image per call. It says nothing about steps or the concise/detailed response_format trade-off beyond what the schema states.

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?

Names a specific verb and resource (image generation from a text prompt) and immediately scopes what it produces: illustrations, mockups, social posts. It also differentiates itself from siblings by naming the excluded cases (image edits, real people's photos) and by pointing at blackwood_image_generate_status for long runs, which only a handful of its 37 siblings do.

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 when-to-use ("Use when you need image generation... from a prompt") and when-not ("Do not use for image edits, specific sizes, photos of real people or more than one image per call"). It also supplies the alternative for the long-running case: the status tool that polls for free. Nothing about tool selection is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Blackwood State toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources