get_trace

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

Annotations already declare readOnly/idempotent/closed-world, so the safety profile is covered. The description adds genuinely useful structure: one entry per round, the fields carried per round, and that steps are ordered — context the annotations cannot convey.

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; the core purpose and the per-round content are front-loaded, and the sibling pointer lands last as a natural follow-up. 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 an output schema present and annotations covering the safety profile, the description supplies everything needed to call it correctly. A minor gap is that it doesn't say whether the trace is bounded/paginated for long-running alerts, but that is largely covered by the output schema.

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?

Only one parameter and schema coverage is 100%, with the schema itself showing the alert id format and example. The description adds nothing about alert_id, so the baseline 3 applies.

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+resource ('investigation history of an alert') and enumerates the exact contents per round (entry point, outcome, proposed fix, model calls, tokens, cost, ordered steps). This clearly delineates it from siblings like get_alert or get_raw_spans.

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?

Explicitly routes the agent to get_raw_spans for full inputs/outputs, which is the key decision point between the two. It doesn't cover the get_alert boundary, but the differentiator that matters (raw vs. summarized trace) is stated.

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