set_denoising

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

With no annotations, the description carries the burden and does well: it discloses that unset parameters are preserved, that the call returns the resulting settings dict, and that OPTIX is restricted to NVIDIA GPUs. It omits failure behavior (e.g., what happens if OPTIX is requested without an NVIDIA GPU) and whether changes persist to the saved file.

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 purpose, then a short rationale, then a compact Args/Returns block that matches the schema order. The '128 vs 2048' sentence is motivating rather than strictly functional, but it is brief and aids the decision to enable denoising.

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?

Seven parameters are all explained and an output schema exists, so return values need little elaboration. The remaining gap is behavioral rather than structural: no annotations means error conditions and persistence semantics are unspecified for a mutation tool.

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 description coverage is 0%, so the description must compensate and fully does: all 7 parameters are documented with meaning beyond the enum values, including hardware constraints for OPTIX, the tradeoffs among prefilter modes, and the fact that RGB_ALBEDO_NORMAL gives the best edges.

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 ('Configure') and resource ('Cycles denoising') plus the two scopes it controls (final renders and viewport). This cleanly separates it from sampling/render-config siblings such as set_render_samples and set_cycles_sampling.

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?

Explains the payoff ('128 denoised samples often beat 2048 raw ones') so the agent knows why to call it, and states partial-update semantics with 'Leave anything unset to keep it.' It does not name an alternative tool or give exclusions (e.g., when to adjust samples instead), so it stops short of a 5.

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