unreal_performance_compare

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

Annotations already mark the operation as read-only and non-destructive. The description adds behavioral context beyond that: it requires matching protocol/project/session/world, reports specific change metrics, and explicitly states the analytical limitation regarding significance and bottleneck detection. This gives an agent useful expectations about what the tool can and cannot conclude.

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 three sentences with no filler. The main action is front-loaded, the reporting behavior is stated next, and the critical limitation closes the description. Every sentence earns its place.

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?

For a read-only comparison tool with an output schema, the description covers what is needed before calling: matching context, required input types, output type, and a key analytical limitation. The annotations cover safety, and the output schema covers return structure, so nothing essential is missing.

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 description coverage is 0%, so the description must compensate. It does connect baseline and candidate to the two timing receipts and 'configured threshold crossings' to maximum_regression_percent, which is helpful. However, it does not explicitly define how the job IDs are used, what 'complete' means for a receipt, or how the regression threshold is applied, leaving partial gaps.

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 names a specific verb ('Compare') and resource ('two complete native timing receipts') with clear scope restrictions (same protocol, project/session, world). It also states what the tool reports (absolute/percent changes and threshold crossings), making it distinguishable from sibling capture/start/cancel tools.

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 clearly implies when to use the tool: when two complete timing receipts from the same context need comparison. It also gives an important exclusion by warning that a pair of captures cannot establish significance or identify bottlenecks. It does not explicitly name an alternative, but the context and limitation are clear.

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