AT Protocol MCP Server

analyze_image

Read-only

Check image blob metadata (MIME, size, format) and get optimization and accessibility suggestions before posting.

Instructions

Analyze an image blob's metadata (MIME type, file size in bytes/KB/MB, derived format, and whether it is within optimized-size thresholds) and optionally return human-readable optimization and accessibility suggestions. Does not decode the image, so it cannot report pixel dimensions or aspect ratio. No authentication required. Use upload_image to obtain the blob reference first, then pass it here; prefer this tool over upload_image for pre-flight size checks before actually posting. Subject to per-tool rate limiting.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`blob`	Yes	Blob descriptor as returned by upload_image (the `image.blob` object in its output): ref (flat CID string or { "$link": "<cid>" } object), mimeType, and size.
`includeOptimizationSuggestions`	No	When true (default), the response includes a list of human-readable optimization and accessibility suggestions based on the blob size and MIME type.

Output Schema

TableJSON Schema

Name	Required	Description
`success`	Yes	True when the analysis completed without errors.
`analysis`	Yes	Metadata derived from the blob.
`suggestions`	No	List of human-readable optimization and accessibility suggestions. Present only when includeOptimizationSuggestions is true.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.6.2Jun 23, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```
removedInput schema / properties / blob / additionalProperties
```
Removed value: -false
```

changedInput schema / properties / blob / properties / ref / anyOf

Previous value: -[
-  {
-    "description": "CID of the uploaded blob as a flat string (e.g. \"bafkrei…\").",
-    "minLength": 1,
-    "type": "string"
-  },
-  {
-    "additionalProperties": false,
-    "description": "Lexicon blob-ref object wrapping the CID as { \"$link\": \"<cid>\" }.",
-    "properties": {
-      "$link": {
-        "description": "CID of the uploaded blob (e.g. \"bafkrei…\").",
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "$link"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "description": "CID of the uploaded blob as a flat string (e.g. \"bafkrei…\").",
+    "minLength": 1,
+    "type": "string"
+  },
+  {
+    "description": "Lexicon blob-ref object wrapping the CID as { \"$link\": \"<cid>\" }.",
+    "properties": {
+      "$link": {
+        "description": "CID of the uploaded blob (e.g. \"bafkrei…\").",
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "$link"
+    ],
+    "type": "object"
+  }
+]

addedInput schema / properties / blob / properties / size / maximum
```
Added value: +9007199254740991
```

Changed15 schema fields changedv0.6.0Jun 11, 2026

addedInput schema / properties / blob / description

Added value: +"Blob descriptor as returned by upload_image (the `image.blob` object in its output): ref (flat CID string or { \"$link\": \"<cid>\" } object), mimeType, and size."

addedInput schema / properties / blob / properties / mimeType / description
```
Added value: +"MIME type of the uploaded blob (e.g. \"image/jpeg\")."
```
addedInput schema / properties / blob / properties / mimeType / minLength
```
Added value: +1
```
removedInput schema / properties / blob / properties / ref / additionalProperties
```
Removed value: -false
```

addedInput schema / properties / blob / properties / ref / anyOf

Added value: +[
+  {
+    "description": "CID of the uploaded blob as a flat string (e.g. \"bafkrei…\").",
+    "minLength": 1,
+    "type": "string"
+  },
+  {
+    "additionalProperties": false,
+    "description": "Lexicon blob-ref object wrapping the CID as { \"$link\": \"<cid>\" }.",
+    "properties": {
+      "$link": {
+        "description": "CID of the uploaded blob (e.g. \"bafkrei…\").",
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "$link"
+    ],
+    "type": "object"
+  }
+]

addedInput schema / properties / blob / properties / ref / description

Added value: +"CID reference of the uploaded blob: either the flat string returned by upload_image, or the lexicon { \"$link\": \"<cid>\" } object form."

removedInput schema / properties / blob / properties / ref / properties
```
Removed value: -{
-  "$link": {
-    "type": "string"
-  }
-}
```
removedInput schema / properties / blob / properties / ref / required
```
Removed value: -[
-  "$link"
-]
```
removedInput schema / properties / blob / properties / ref / type
```
Removed value: -"object"
```
addedInput schema / properties / blob / properties / size / description
```
Added value: +"Size of the uploaded blob in bytes."
```
addedInput schema / properties / blob / properties / size / exclusiveMinimum
```
Added value: +0
```
changedInput schema / properties / blob / properties / size / type
```
Previous value: -"number"New value: +"integer"
```

addedInput schema / properties / blob / properties / type

Added value: +{
+  "const": "blob",
+  "description": "Discriminator emitted by upload_image; always \"blob\" when present. May be omitted.",
+  "type": "string"
+}

addedInput schema / properties / includeOptimizationSuggestions / description

Added value: +"When true (default), the response includes a list of human-readable optimization and accessibility suggestions based on the blob size and MIME type."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "analysis": {
+      "description": "Metadata derived from the blob.",
+      "properties": {
+        "format": {
+          "description": "Format string derived from the MIME type subtype (e.g. \"jpeg\", \"png\", \"webp\").",
+          "type": "string"
+        },
+        "isOptimized": {
+          "description": "True when the blob is within the format-specific size threshold considered optimized for web use.",
+          "type": "boolean"
+        },
+        "mimeType": {
+          "description": "MIME type of the image as declared in the blob (e.g. \"image/jpeg\").",
+          "type": "string"
+        },
+        "size": {
+          "description": "Raw blob size in bytes.",
+          "type": "number"
+        },
+        "sizeKB": {
+          "description": "Blob size converted to kilobytes, rounded to two decimal places.",
+          "type": "number"
+        },
+        "sizeMB": {
+          "description": "Blob size converted to megabytes, rounded to two decimal places.",
+          "type": "number"
+        }
+      },
+      "required": [
+        "mimeType",
+        "size",
+        "sizeKB",
+        "sizeMB",
+        "format",
+        "isOptimized"
+      ],
+      "type": "object"
+    },
+    "success": {
+      "description": "True when the analysis completed without errors.",
+      "type": "boolean"
+    },
+    "suggestions": {
+      "description": "List of human-readable optimization and accessibility suggestions. Present only when includeOptimizationSuggestions is true.",
+      "items": {
+        "description": "A single optimization or accessibility recommendation.",
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "success",
+    "analysis"
+  ],
+  "type": "object"
+}

Changed1 schema field changedv0.3.0Jun 9, 2026
- removedInput schema / $schema
```
Removed value: -"http://json-schema.org/draft-07/schema#"
```
First observedv0.2.1Jun 2, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Discloses limitations (does not decode image, no pixel dimensions) and rate limiting, adding value beyond readOnlyHint and openWorldHint annotations. No contradictions with annotations.

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 sentences covering all essentials: what it does, prerequisites, limitations, usage preference, and rate limiting. No unnecessary words.

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 output_schema exists (so return values need no explanation), annotations provide safety context, and schema covers all parameters, the description is complete: it tells what to do, prerequisites, limitations, and alternatives.

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%, baseline 3. The description adds context by explaining the blob parameter as a result from upload_image and the includeOptimizationSuggestions parameter's default behavior, but parameter details are already well-covered by schema.

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 description clearly states the tool analyzes image blob metadata (MIME type, size, derived format, optimization thresholds) and optionally returns suggestions. It explicitly distinguishes from siblings by noting it does not decode the image and cannot report pixel dimensions, and differentiates from upload_image for pre-flight checks.

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?

Provides explicit guidance: use upload_image first, then pass the blob reference; prefer this tool over upload_image for pre-flight size checks; notes no authentication required and rate limiting.

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