Triage Cluster/Namespace/Workload

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

With no annotations, the description carries the full burden: it is transparent about scope (aggregate over many signals) and the default window of 30m, which hints at cost/breadth but never states it. It omits the safety profile (read-only?), any permissions/auth requirements, rate limits, or whether this is an expensive fan-out query. Useful but incomplete behavioral context for a heavy multi-signal aggregate.

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 dense sentences, front-loaded with the tool's identity ('SRE snapshot without a problem id'), followed by a tight signal list and then the invocation precondition and default. No filler; every clause carries information for selection or invocation.

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 13-param, no-annotation, no-output-schema aggregate tool, the description covers what is collected, the default window, and that discovery must precede invocation. It does not clarify that cluster/namespace are effectively required despite 0 required params in schema, nor hint at the response shape, but it is largely complete for correct invocation.

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 100% (13 params, all documented), so the baseline is 3. The description reinforces that cluster/namespace/workload are the inputs to pass and points to discovery tooling, and notes the 30m default window, but adds no syntax beyond what the schema already gives.

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 definition gives a specific verb+resource ('SRE snapshot') and enumerates exactly what it aggregates: Davis problems, OOM/CrashLoop events, ERROR counts, quota hotspots, replica mismatch, restarts, golden signals, failed spans. The phrase 'without a problem id' cleanly distinguishes it from the sibling dynatrace_triage_problem, so an agent can route without opening either schema.

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 frames the use case ('without a problem id') and tells the caller to pass cluster/namespace/workload and to discover first, which is the key precondition. It stops short of naming explicit alternatives/exclusions (e.g., 'if you have a problem id use dynatrace_triage_problem', or when a single focused tool like dynatrace_k8s_events is preferable), so it is clear context rather than full routing guidance.

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