perf

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It explains the artifact lifecycle for CPU profiles (start/stop vs report), and states that profiling output is evidence only with compact state, artifact path, and size. It doesn't cover all areas but discloses key behavioral traits.

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?

Four sentences, front-loaded with the main purpose, and each sentence adds scope, usage guidance, or output characteristics. No filler or redundancy.

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 is a complex tool with 31 parameters and no output schema. The description covers the CPU workflow and output shape but doesn't detail metrics, memory, frames, or platform-specific behavior. The rich schema compensates for parameter details, making it adequate but not exhaustive.

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 87% with enums for action, area, and kind, so the baseline is 3. The description adds semantic meaning by explaining what start/stop/report actions produce, enriching the action parameter beyond the schema's enum list.

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 and resource ('Collect session performance metrics, frame health, memory diagnostics, and platform profiling artifacts'), clearly stating what perf does. It doesn't explicitly differentiate from sibling tools like 'trace', but the scope is well-defined.

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: prefer structured metrics for first-pass diagnosis, and for CPU profiles start/stop write the raw artifact while report writes a compact summary, with instruction to request the report when readable native CPU evidence is needed. This goes beyond implied usage to actionable alternatives.

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