Tanod

imagepeek: compress an image (optionally to a byte budget)

image_compress

Idempotent

imagepeek: Compress an image, optionally to a byte budget. To change the format only use image_convert. Returns a smaller JPEG, WebP, AVIF or PNG (or original if not smaller). With max_bytes, default fit: quality keeps dimensions; fit: downscale tries up to 6 aspect-preserving reductions, quality >=10, min_side=256, never upscales, one time budget. Check target_met. Reads PNG, JPEG, WebP, GIF, TIFF, BMP, ICO and AVIF; other formats and images over 40 megapixels are refused (not charged). Output: base64 data_base64, without EXIF, GPS, XMP or IPTC; over 15 MB or 50 megapixels is a 413 (not charged). Images are not logged; a result is kept only with output "url" (24 h). Typically 0.5-2 s. Price: USD 0.003. Free: 3 imagepeek calls per IP per UTC day. Docs: https://tanod.dev/learn/image-compress-api.html

Input Schema

Name	Required	Description	Default
`fit`	No	Requires max_bytes when supplied. quality (default) keeps dimensions; downscale tries up to 6 smaller sizes with the same aspect ratio, searching quality >= 10 at each size under one time budget. Check target_met; fitting is not guaranteed. Downscale requires quality >= 10 if set.	quality
`url`	No	Public http(s) URL of the image (at most 10 MB; private, internal and IP-literal hosts are refused); or use image_base64.
`colors`	No	png: quantise to this many colours.
`format`	No	Output format: jpeg, png, webp or avif (default: the input's).
`output`	No	base64 (default): the file comes back inline as base64. url: the file is stored for 24 hours and the reply carries a download link (url, expires_at, bytes, content_type, sha256) instead of the base64, which keeps the file out of your context window.	base64
`quality`	No	Target (or, with max_bytes, highest) quality.
`keep_icc`	No	Keep the ICC colour profile (default true).
`lossless`	No	webp only: lossless encoding (default false).
`min_side`	No	downscale only: shortest-side floor in pixels (1-32768, default 256). Inputs already below this floor are not resized; never upscales.
`max_bytes`	No	Size target: the highest quality that fits.
`auto_orient`	No	Apply the EXIF orientation first (default true).
`progressive`	No	jpeg only: progressive encoding (default false).
`image_base64`	No	The image as standard or url-safe base64 (at most 10 MB decoded; a data:image/...;base64, prefix is fine); or use url.

Output Schema

Name	Required	Description
`url`	No
`bytes`	No
`error`	No	Only on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object.
`input`	No
`notes`	No
`width`	No
`format`	No
`height`	No
`sha256`	No
`source`	No
`encodes`	No
`final_url`	No
`operation`	No
`expires_at`	No
`source_url`	No
`target_met`	No
`after_bytes`	No
`data_base64`	No
`saved_bytes`	No
`saved_ratio`	No
`before_bytes`	No
`content_type`	No
`quality_used`	No
`scale_factor`	No	downscale only: uniform scale relative to the EXIF-oriented input, before rounding dimensions; 1 for an unchanged original.
`downscale_steps`	No	downscale only: smaller sizes searched (0-6).
`returned_original`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 27, 2026

addedInput schema / properties / fit

Added value: +{
+  "default": "quality",
+  "description": "Requires max_bytes when supplied. quality (default) keeps dimensions; downscale tries up to 6 smaller sizes with the same aspect ratio, searching quality >= 10 at each size under one time budget. Check target_met; fitting is not guaranteed. Downscale requires quality >= 10 if set.",
+  "enum": [
+    "quality",
+    "downscale"
+  ],
+  "title": "Fit",
+  "type": "string"
+}

addedInput schema / properties / min_side

Added value: +{
+  "default": 256,
+  "description": "downscale only: shortest-side floor in pixels (1-32768, default 256). Inputs already below this floor are not resized; never upscales.",
+  "maximum": 32768,
+  "minimum": 1,
+  "title": "Min Side",
+  "type": "integer"
+}

addedOutput schema / properties / downscale_steps

Added value: +{
+  "description": "downscale only: smaller sizes searched (0-6).",
+  "type": [
+    "integer",
+    "null"
+  ]
+}

addedOutput schema / properties / scale_factor

Added value: +{
+  "description": "downscale only: uniform scale relative to the EXIF-oriented input, before rounding dimensions; 1 for an unchanged original.",
+  "type": [
+    "number",
+    "null"
+  ]
+}

Changed4 schema fields changedOct 12, 2026

addedInput schema / properties / output

Added value: +{
+  "default": "base64",
+  "description": "base64 (default): the file comes back inline as base64. url: the file is stored for 24 hours and the reply carries a download link (url, expires_at, bytes, content_type, sha256) instead of the base64, which keeps the file out of your context window.",
+  "enum": [
+    "base64",
+    "url"
+  ],
+  "title": "Output",
+  "type": "string"
+}

addedOutput schema / properties / expires_at

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / sha256

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / url

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

Changed7 schema fields changedOct 8, 2026

addedInput schema / properties / auto_orient / description

Added value: +"Apply the EXIF orientation first (default true)."

addedInput schema / properties / format / description

Added value: +"Output format: jpeg, png, webp or avif (default: the input's)."

addedInput schema / properties / keep_icc / description

Added value: +"Keep the ICC colour profile (default true)."

addedInput schema / properties / lossless / description

Added value: +"webp only: lossless encoding (default false)."

addedInput schema / properties / progressive / description

Added value: +"jpeg only: progressive encoding (default false)."

changedInput schema / properties / url / description

Previous value: -"Public http(s) URL of the image (at most 10 MB); or use image_base64."New value: +"Public http(s) URL of the image (at most 10 MB; private, internal and IP-literal hosts are refused); or use image_base64."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "after_bytes": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "before_bytes": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "bytes": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "content_type": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "data_base64": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "encodes": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "error": {
+      "description": "Only on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object."
+    },
+    "final_url": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "format": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "height": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "input": {
+      "properties": {
+        "animated": {
+          "type": [
+            "boolean",
+            "null"
+          ]
+        },
+        "bytes": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "format": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "frames": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "has_alpha": {
+          "type": [
+            "boolean",
+            "null"
+          ]
+        },
+        "height": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "width": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        }
+      },
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "notes": {
+      "items": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "type": [
+        "array",
+        "null"
+      ]
+    },
+    "operation": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "quality_used": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "returned_original": {
+      "type": [
+        "boolean",
+        "null"
+      ]
+    },
+    "saved_bytes": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "saved_ratio": {
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "source": {
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "source_url": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "target_met": {
+      "type": [
+        "boolean",
+        "null"
+      ]
+    },
+    "width": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}

AddedOct 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=true) by disclosing refusal conditions (>40 MP, unsupported formats), metadata stripping (EXIF/GPS/XMP/IPTC), a 413 ceiling at 15 MB or 50 MP, that oversized inputs are not charged, privacy (images not logged), 24 h retention only for `output: url`, latency, price and a free tier. These are exactly the operational facts an agent needs before invoking a billed, network-dependent tool.

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-loads purpose and the sibling routing before the operational detail, and sentences are densely informative. It is long and slightly cluttered by pricing/docs/free-tier text mid-paragraph, but almost every sentence carries a decision-relevant fact.

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 13-parameter, billed, open-world image transform, it covers inputs, supported formats, refusal paths, output shape, retention and cost. An output schema exists, so return structure needn't be spelled out, and the `target_met` and `data_base64` mentions are bonus rather than obligation.

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 description coverage is 100%, so every one of the 13 parameters is already documented; the description only reiterates the `fit`, `min_side`, quality floor and `output` behavior. The one genuine addition is pointing at the `target_met` result field, which the schema does not carry. Baseline 3 is appropriate since the schema does the heavy lifting.

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 ('Compress an image') plus the key scope modifier ('optionally to a byte budget'), and explicitly routes format-only work to the sibling image_convert. An agent can distinguish it from image_convert, image_resize and image_thumbnail from the description alone.

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?

Names the alternative (image_convert) with the triggering condition ('to change the format only'), and explains the two modes: default `fit: quality` keeps dimensions, `fit: downscale` performs aspect-preserving reductions. It also notes checking `target_met` because fitting is not guaranteed, so the agent knows the outcome is conditional.

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

All Tanod tools Inspect

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

Need Help?