Skip to main content
Glama

Generate Depth Map

sirv_generate_depth_map

Generate a greyscale depth map from one image, with lighter areas closer and darker areas farther, for parallax, relighting, or 3D effects.

Instructions

Make a greyscale depth map from one image. Lighter areas are closer and darker areas are farther away.

Use it for parallax, relighting or 3D effects. Do not use it to make a 3D model (use sirv_generate_3d_model) or to edit the image (use sirv_edit_image).

Input: image_url, the public URL of one image. It is the only input. The same image gives the same depth map.

Studio also saves the depth map in the library as a new asset. Returns result_url.

Credits: free.

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": {
      "image_url": "<image_url>"
    },
    "name": "sirv_generate_depth_map"
  }
}

Input Schema

NameRequiredDescriptionDefault
image_urlYesPublic URL of the image to make a depth map from

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.1

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only declare the generic profile (write, open-world, not destructive). The description adds real behavioral context: the tool writes a new asset into the library as a side effect, returns result_url, and costs no credits. The note that 'the same image gives the same depth map' describes output determinism while the 'new asset' line correctly explains why the call itself is not idempotent, so it is consistent with idempotentHint=false rather than contradicting it.

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?

Four short blocks — what it does, when to use it, the input contract, and cost/return — with the purpose front-loaded and zero filler. Every sentence carries information an agent needs.

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 one-parameter generative tool with no output schema, the description still covers the output appearance, the return field (result_url), the library side effect, and the credit cost. Nothing required to call it correctly 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 the single parameter is already documented as a public URL, so the description's added value is modest. It does reinforce that image_url is the sole input and that the URL must be public, which prevents an agent from inventing extra options.

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 ('Make a greyscale depth map from one image') and immediately characterizes the output ('Lighter areas are closer and darker areas are farther away'). It also names the two siblings it is not, so an agent can distinguish it from sirv_generate_3d_model and sirv_edit_image without opening any 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?

Gives positive use cases ('parallax, relighting or 3D effects') and explicit exclusions with the correct alternative for each ('Do not use it to make a 3D model (use sirv_generate_3d_model) or to edit the image (use sirv_edit_image)'). This is the when/when-not/alternative pattern at full strength.

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