run_js

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

Discloses runtime-only behavior, warns about mutations, and gives shader patching steps. Adds significant context beyond annotations (destructiveHint=true) by explaining when to ask user and that changes are lost on reload.

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?

Description is long due to detailed shader patching recipe, which could be moved to documentation. However, front-loaded with core purpose and usage guidelines. Some redundancy (e.g., 'Runtime only' appears twice). Could be more concise.

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?

Covers execution environment, return value, mutability warning, and reset behavior. No output schema but return value explained. Shader recipe adds depth. Slightly less complete in explaining error handling or side effects beyond scene mutation.

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 covers 100% of parameter description. Description adds available variables and usage hint but does not substantially extend beyond schema's 'JavaScript code. Available vars: scene, renderer, camera, gl. Use return for results.' Baseline 3.

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?

Clearly states it executes arbitrary JavaScript with access to scene, renderer, camera, and returns the result. Distinguishes from sibling tools that are more specific (e.g., set_uniform, material_details).

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?

Provides explicit guidance: ask user before mutating scene state, debug only, reset on reload. Includes detailed shader patching recipe. Lacks direct comparison to alternatives but context implies unique role.

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