set_post

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

Beyond the destructiveHint=true annotation, the description discloses a lot: it builds a compositor tree, works with every engine, is invisible in the viewport, applies deltas rather than replacing settings, uses false to disable an individual effect, reset=true removes everything it set, and it 'refuses to replace a compositor tree it did not make'. This is exactly the extra context annotations cannot express.

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?

Front-loaded with the core purpose and update semantics before the dense per-parameter block; every clause adds information. The parameter block is somewhat run-on, but the density is justified given 6 undocumented parameters.

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 complex mutation tool with six undocumented parameters and no output schema, the description covers purpose, update semantics, per-effect meaning, safety constraints, and even the return ('Returns the active settings'). Nothing an agent needs 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.

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

Schema coverage is 0%, so the description carries the full burden and does: it gives ranges and defaults for vignette strength/softness (0-1, start 0.5), glare type (bloom/fog_glow/streaks), threshold, size (1-9, 8 when empty), color saturation/gamma, exposure in stops, contrast (-1 to 1). This fully compensates for the empty schema.

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?

States a specific verb (set) and resource (post-processing for render_final), then enumerates the exact effects (vignette, glare, colour, exposure, contrast). It clearly distinguishes itself from sibling render tools like render_final and setup_lighting, which do the actual rendering or lighting rather than post effects.

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 'for render_final' framing and the disclosure that it is 'not shown in the viewport' establish when this applies, and 'A call changes only what you pass and keeps the rest' plus reset=true describes the update semantics clearly. It stops short of naming an explicit alternative tool or a when-not condition, so it does not reach 5.

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