performance_audit_gpu

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

With no annotations, the description carries the burden; it communicates low-impact behavior ('lightweight') and a non-destructive read pattern via 'audit snapshot' and 'Returns'. It stops short of explicitly stating 'does not modify project state' or listing editor-session requirements, but the implied behavior is clear for a diagnostic tool.

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?

Every line earns its place: purpose and returns, alternative, parameter semantics, KB pointer, and a no-arg example. Decision-relevant content is front-loaded, and there is no redundant restatement of the schema defaults.

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?

An output schema exists, so return details are covered elsewhere, and the description handles the remaining invocation context: what data is included, control via optional booleans, and when deep pass timings are needed. The KB reference and example complete the picture.

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?

Despite 0% schema description coverage, the Args block explains both parameters in plain terms: include_memory maps to process/platform memory stats and include_viewport to active viewport dimensions and viewmode. This adds real semantic value over the bare boolean titles.

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 verb-resource pair is explicit ('Capture a lightweight editor GPU/performance audit snapshot') and the return list makes the scope concrete. It distinguishes itself from ProfileGPU by explicitly deferring pass timings, but it does not name a sibling like shader_analyze_complexity or renderer_capture_viewmode, so differentiation within the sibling set is left to inference.

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 first sentence frames when to use it for a lightweight performance snapshot, and the ProfileGPU sentence is an explicit when-not/alternative for pass timings. This is enough for an agent to route between a broad audit snapshot and deep profiling.

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