start_trace

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

Annotations already declare idempotentHint=true and destructiveHint=true, so the safety profile is partly covered. The description then adds genuine value by spelling out what the idempotency actually means ('returns already_tracing:true with the current destination instead of failing'), which the hint alone does not convey. It still says nothing about permissions, cost, or why destructiveHint is set.

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 tight sentences plus a compact return-value line. The core purpose is front-loaded, and every clause (idempotency behavior, return shape) earns its place. No filler.

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?

With no output schema, the description helpfully enumerates the return object fields (tracing, already_tracing, destination, channels, note), and it covers the idempotent behavior. What remains thin is the surrounding lifecycle context (how to stop or inspect the trace), but for a single-param operation this is largely complete.

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 100% and both parameters (channels, output_path) are fully documented in the schema, including the default channel list and default output path. The description adds no parameter-level meaning beyond that, so the baseline of 3 is appropriate.

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?

States a specific verb and resource ('Start an Unreal Insights trace recording to a .utrace file'), which is clear and unambiguous. It does not explicitly differentiate itself from likely siblings such as stop_trace, get_trace_status, or list_traces, but the action is distinct enough that an agent can tell them apart.

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?

Usage context is implied by 'Start an Unreal Insights trace recording,' but there is no explicit when-to-use guidance, no prerequisites (e.g. required editor state), and no mention of the sibling tools that stop or query a trace. The idempotency note gives behavioral context but not selection guidance.

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