trace

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

With no annotations, the description carries the behavioral burden and does disclose meaningful behavior: the start/stop state machine, artifact return at end of capture, artifact path pairing, and a 90-second timeout. It does not mention any side effects or permission requirements, but the self-contained behavior is well covered.

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?

Three sentences, each carrying distinct information: the core capability, the path-pairing rule, and the timeout. The most important verb and resource are front-loaded.

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 stateful capture tool, it covers the essential operational concerns (start/stop, artifact path, return timing, timeout) and an output schema exists. It could be more explicit about the start response versus the stop response, but nothing critical is missing for invoking correctly.

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 89%, so the schema already documents most parameters. The description adds value beyond that by explaining that path must be shared between matching start and stop requests, which is not evident from the schema alone.

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 identifies a specific action (start/stop trace-log capture) and a concrete outcome (returning the resulting artifact), so an agent knows what the tool does. It does not explicitly differentiate trace from sibling tools like record or perf, but the trace-log capture resource is distinctive enough to avoid most ambiguity.

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 gives clear operational context: start or stop capture, reuse the same artifact path across matching requests, and expect completion within 90s. It does not list alternative sibling tools or when-not conditions, which prevents a 5.

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