open_depth_image

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

With all annotation hints false, the description carries the full burden and does so thoroughly: it discloses calibration requirements, supported formats, optional auxiliary files, camera-append behavior via scene_id, COLMAP calibration sourcing, and the fact that picks/exports preserve original coordinates and raw values. This is rich behavioral context beyond the structured annotations.

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

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

The description is dense and front-loaded with the core purpose, then efficiently covers formats, optional inputs, special modes, and diagnostic behavior. Every sentence carries useful information, though the length and reliance on domain-specific shorthand like 'viewer://depth-calibration' make it slightly less immediately digestible.

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

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

For a tool with eight parameters, many formats, and special COLMAP behavior, the description covers the critical invocation details and references an output schema for results. It leaves minor gaps such as the exact default camera action when scene_id is omitted and the meaning of colmap_variant, but the overall context is strong.

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

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

Although main-schema parameter descriptions are 0% covered, the description compensates by addressing path, rgb, confidence, mask, scene_id, colmap_image, and calibration behavior. The calibration object itself is well documented in the schema's $defs, so the main gap is colmap_variant, which is at least self-explanatory through its enum.

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

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

The description states a specific verb ('Project') and resource ('a depth/disparity raster inline'), and clarifies the tool's distinctive role among the 3D-viewer siblings: it loads depth/disparity rasters with explicit calibration, not general 3D files or scenes. It is immediately clear what this tool does and how it differs from tools like open_3d_files or read_viewer_data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool, including optional RGB/confidence/mask inputs, the scene_id append behavior, and the special COLMAP dense-workspace mode with path=workspace and colmap_image. It does not explicitly name alternatives or state when not to use it, so it stops short of full exclusion guidance.

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