get_trace

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds a genuine behavioral detail (results are chronological spans of a single trace), but says nothing about pagination, the time-window default, or what happens when the trace_id is unknown.

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 with no filler, and the core action ('Get the spans of one distributed trace') is front-loaded ahead of the optional pairing hint.

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?

The output schema exists, so return values need not be described. But for a tool whose behavior depends heavily on an undocumented default time window (since=3 HOURS AGO) and limit, the description leaves an agent unable to predict what a bare call will return.

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 only 25% – only trace_id is documented in the schema. The description names trace_id in the pairing sentence but adds no meaning for the three other parameters (limit, since, account_ids), leaving the 3-hour default time window and the 1000-span cap entirely unexplained.

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 states a specific verb and resource ('Get the spans of one distributed trace') plus the ordering guarantee ('in chronological order'), so an agent knows exactly what it returns. It also implicitly distinguishes itself from the log-oriented siblings by naming search_logs as the complementary 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?

It gives one concrete usage pairing ('Pair this with search_logs on the same trace_id'), which is useful context. However, it offers no guidance on when this is preferable to other exploration tools (get_entity, run_nrql, search_entities) and no exclusions or prerequisites.

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