Slow Spans

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

No annotations are provided, so the description carries the full burden. It discloses a latency ranking and the workload window ('in the window') but not whether the query is bounded by the default range cap (only the allowLongRange param hints at this), whether results are trial/billing-limited (Grail budget sibling exists), or what the return shape looks like.

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 short, front-loaded sentences with no filler: purpose first, follow-up action second. Under- rather than over-specified for an 11-param tool, but no wasted clauses.

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 an 11-parameter, no-annotation, no-output-schema tool, the description is thin. It does not explain the range cap/default, the relationship to dynatrace_failed_spans (choosing which span-ranking tool), or the result fields an agent needs to pivot to dynatrace_get_trace.

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 91%, so time-range semantics for window/around/from/to, service, namespace, and limit are largely documented in the schema. The description adds 'in the window' scoping context but nothing about the placeholder 'row' identifiers or which params affect ranking.

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 resource (spans) and a clear ranking/mode ('highest-duration', latency triage). The parenthetical '(latency triage)' hints at intent, distinguishing it somewhat from dynatrace_failed_spans, but the distinction between slow vs failed is implied rather than explicit.

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?

Gives a follow-up action ('Follow a row with dynatrace_get_trace') but no when-to-use/how-not guidance or explicit comparison to the adjacent sibling dynatrace_failed_spans (error triage vs latency triage). The triage hint is present but the alternative tool is not named.

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