3D-aware post-processing passes

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

The description goes far beyond the minimal annotations (readOnly=false, destructive=false). It discloses fixed execution order, fallback behaviors (SSR skip, motion blur directional fallback), auto-creation of a depthTOP, and the exact return payload (paths, enabled passes, warnings). This is rich contextual behavior.

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 a single dense paragraph where each sentence contributes new information: pipeline construction, per-pass implementation, order, fallbacks, auto-depth creation, and return values. It is efficient and well-structured for the complexity.

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 17 parameters and complex chain behavior, the description covers the main workflow, fallback paths, and return values. It lacks detailed explanation for many parameters, but the schema provides names, defaults, and constraints, so the description is mostly complete.

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?

Schema coverage is low (35%), but the description adds meaningful semantics for the AOV inputs: depth_top auto-derivation, normal_top empty triggers SSR skip, velocity_top empty triggers fallback. However, it says nothing about the many numeric/boolean controls (ssao_radius, dof_aperture, etc.), which rely on self-evident names and schema defaults.

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 opens with a specific verb and resource: 'Compose a chain of 3D-aware post-processing passes inside a new baseCOMP.' It names the exact passes (SSAO, SSR, DOF, motion blur) and the container type, and the fixed order differentiates it from generic post-processing siblings like apply_post_processing.

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 implies the tool is for building a 3D-aware post-processing chain but never explicitly contrasts it with alternatives or states when to use it vs. other compositing tools. It provides detailed behavior but no exclusions or alternative recommendations.

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