manage_performance

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

Annotations only indicate readOnlyHint=false, destructiveHint=false, and idempotentHint=false, which are uninformative (all false). The description adds no behavioral context: it does not mention whether settings changes are persistent, whether profiling requires a running editor session, whether actions like merge_actors modify the scene destructively, or what side effects may occur. With no helpful annotations, the description should disclose such traits but does not.

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 sentence, front-loaded with action verbs ('Run profiling/benchmarks, configure...'), and contains no unnecessary words. It is appropriately concise and readable. However, given the tool's complexity, a slightly longer structured description might add value, but this does not detract from its conciseness.

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?

This tool has 30 parameters and 20 distinct actions, yet the description covers only a fraction of its capability. There is no output schema, and annotations are minimal. The description does not explain return values, action-specific parameter dependencies, or typical usage flows (e.g., start_profiling then stop_profiling). It is far from complete for such a complex 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?

The input schema has 30 parameters, but only 10% have descriptions (action, enabled, outputPath). The description mentions 'scalability, LOD, Nanite, and optimization settings' which loosely map to some parameters, but it does not explain the meaning or purpose of key parameters such as hzb, type, level, scale, lodBias, maxPixelsPerEdge, streamingDistance, etc. Given the low schema coverage, the description was expected to compensate, but it does not.

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 clearly states the tool's purpose: 'Run profiling/benchmarks, configure scalability, LOD, Nanite, and optimization settings.' It uses specific verbs (run, configure) and distinct resources (profiling, benchmarks, scalability, LOD, Nanite, optimizations), which differentiates it from sibling tools like manage_asset or manage_level. It is not a tautology and gives a functional overview, though it is broad and does not enumerate all 20 actions.

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 provides no guidance on when to use this tool versus alternatives. It does not mention any preconditions, exclusions, or scenarios where another tool would be more appropriate. For example, it does not say 'Use this for performance diagnostics; use manage_settings for general config.' This leaves the agent without explicit usage direction.

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