runTests

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

Beyond the minimal annotations (readOnlyHint=false, destructiveHint=false), the description discloses two important behaviors: it activates the class first (a side effect) and that a bare run on an inactive object returns an empty list that falsely appears successful. This is valuable trap-warning context that annotations do not provide. The promise of a summary and on-request full ADT result also adds behavioral clarity.

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?

The description is two sentences and front-loads the primary action. The critical empty-list warning is well placed. The meta-comment 'This is what unitTestRun should feel like' is slightly extraneous and could be trimmed without loss, but overall the structure is efficient and the key information is prominent.

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 description covers the core behavior: activation, the empty-list trap, the summary contents, and the raw option. The nested 'flags' object is left to the schema, which already describes it. Given the tool's complexity and absence of an output schema, the description provides enough context for an agent to understand expected results and side effects. Only missing an explicit mention of when to prefer this over unitTestRun, which is a minor gap.

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 coverage is 100%, so all parameters are already described in the input schema. The description adds little about parameters themselves—it mentions the 'raw' option indirectly ('full ADT result available on request') but that duplicates the schema's 'Include the full ADT result alongside the summary.' No new semantic depth is provided beyond what the schema already conveys, 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?

The description clearly states that it runs ABAP Unit tests for a class and reports results, with a specific verb and resource. It also mentions activation behavior, which helps distinguish it from a plain 'run tests' operation. However, it does not explicitly name a sibling alternative like unitTestRun, so it's not fully differentiated, though the added context about the empty-list trap separates it.

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 useful context about what happens with inactive objects and the need for activation, which indirectly guides usage. But it does not explicitly state when to use this tool versus siblings like unitTestRun or unitTestEvaluation, nor when to avoid it. No alternatives are named, so the guidance is implied rather than explicit.

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