Analyze GPU Trace PC samples and stalls

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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering safety. The description adds valuable context beyond those: that no shader PDBs are required and source-line correlation is not claimed, which sets expectations for accuracy and input requirements. No contradictions with annotations.

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?

Two sentences, front-loaded with the primary action, followed by scoping and limitations. Every sentence adds value, and there is no redundancy with the schema or annotations.

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?

Despite lacking an output schema, the description conveys expected results (sample/stall reasons, code-block attribution, hotspots). It covers purpose, temporal scoping, and a key prerequisite. It could be more complete by detailing parameter interactions (e.g., marker_id vs time range), but for a polished tool description, it is largely sufficient.

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 coverage is 56%, leaving 4 parameters without descriptions. The description compensates for time-window parameters (start_ms, end_ms, marker_id) by explaining frame-relative and marker scoping, and it hints at output parameters (top_shaders, top_pcs). However, it does not explain stage or shader_hash semantics, which the schema only minimally covers.

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 uses a specific verb ('Decode raw PC-sampling records into sample/stall reasons, exact shader/code-block attribution, and top shader and instruction-PC hotspots') and clearly identifies the resource. It distinguishes from siblings like summarize_gpu_trace_range by narrowing to PC-sampling analysis.

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?

It explicitly states scoping options (entire trace, frame-relative window, marker id) and adds a limitation ('does not require shader PDBs; source-line and SASS text correlation are not claimed'). It doesn't name alternative tools, but the context is clear enough to infer when this tool applies.

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