tracesStatements

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

Annotations already mark this as read-only and non-destructiveasi. The description adds meaningful behavior beyond that: the recording-flag prerequisite, a hard backend refusal for aggregated traces, a cap on returned statements, and the scale of 'some 8000 statements' per ADT call. It does not describe the exact return format, but the annotations lower the bar for safety-related disclosure.

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, all with distinct information: what the tool returns, where the id comes from and a prerequisite, and how the capped output interacts with heaviestFirst. There is no filler or repetition of schema details, and the core purpose is 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 read-only tool with a fully documented schema illegivel, this is a solid definition. It covers the input source, a key failure condition, scale, and optional sorting. It does not explain the shape of the returned statements, but no output schema exists and the phrase 'statements... with their times' gives a basic mental model.

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?

The input schema already documents all four parameters, so the baseline is 3. The description adds value by linking id to tracesList, explaining why heaviestFirst matters in the context of a capped response, and giving scale context behind the limit parameter. Most parameter meaning comes from the schema, but the extra rationale helps an agent choose the right parameter behavior.

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 clearly identifies the resource: the statements of one trace, with times, and adds the evocative 'where a run spent itself.' It lacks an explicit imperative verb like 'returns' or 'lists,' but it is far from a tautology and conveys the purpose well. The phrase 'Takes a trace id from tracesList' also positions it relative to the sibling tracesList tool.

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 gives actionable context: pass a trace id from tracesList except when aggregate true, because the backend refuses statements for aggregated traces. It also advises using heaviestFirst when interested in the expensive end of a capped result. It does not name an alternative tool for the aggregated case, but the guidance is clear enough.

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