set_eevee_quality

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

With zero annotations the description carries the full burden, and it does disclose the key mutation semantics: unset fields are preserved, and the return is a dict of the post-change settings. It omits meaningful behavioral facts — that these are scene-level writes requiring the EEVEE engine to be active, whether changes are permanent until saved, and whether a viewport refresh is required.

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 a one-line purpose followed by a scoping rule, then a well-formatted per-argument block where every line earns its place given 0% schema coverage. Slightly long, but the length is justified by 12 undocumented parameters rather than padding.

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?

The parameter documentation is strong and an output schema exists, so return values need no further explanation. However, for a 12-parameter scene-mutating tool with no annotations, the description never states that the scene must be using EEVEE, which scene is affected, or how it relates to set_eevee_light_path — gaps that could cause an agent to call it uselessly under Cycles.

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%, and the description fully compensates: all 12 parameters are explained with units, valid ranges and enumerated values (shadow_pool_size 16–2048 powers of two plus 1536, shadow_rays 1–4, shadow_steps 1–16, volumetric_samples 1–256, tile sizes 1/2/4/8/16), plus the meaning of both enum parameters. It also adds practical guidance the schema cannot express ("raise it if shadows go blocky", "smaller is sharper and slower").

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 ("Tune") and a specific resource set (EEVEE reflections, GI, shadows, volumes), which clearly separates it from general scene/render tools like set_render_engine or set_render_samples. It does not, however, distinguish itself from plausible siblings such as set_eevee_light_path or set_shadow_settings, so an agent must infer the boundary.

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?

"Leave anything unset to keep it" is a genuinely useful partial-update rule and implies this is an adjust-in-place tool rather than a full reset. But there is no explicit when-to-use guidance, no stated prerequisite (e.g. EEVEE must be the active engine), and no routing to or away from sibling tools.

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