RunATC

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

With no annotations, the description carries the full burden and does well: it discloses the side effect of creating a worklist, that the server blocks on wait=true versus returning a run_id on wait=false, and that findings remain readable either way. It omits authorization/permission requirements and any cost or runtime caveats for large packages.

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?

Three tight sentences with the action front-loaded, followed by the mechanism and then return-value behavior. No filler, and each sentence carries new information.

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?

No output schema exists, so the description correctly compensates by specifying exactly what is returned (worklist_id always, run_id when wait=false, finding counts when wait=true) and which siblings read those values. An agent has everything needed to call it and chain follow-ups.

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 wait, objects, max_findings and check_variant are already documented in the schema. The description restates the wait semantics (mildly redundant) and does not mention max_findings or check_variant at all, so it adds little beyond the structured fields. 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 and resource ('Run ABAP Test Cockpit checks over one or more objects') plus the internal mechanism (worklist creation then run start). It differentiates itself from siblings by naming GetATCFindings and GetATCRunStatus as the consumers of its output.

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 wait=true/false sentence gives concrete selection guidance, and naming GetATCFindings and GetATCRunStatus tells the agent where to go next. It stops short of stating when not to run ATC at all (e.g., versus the per-object Check* tools), so it is clear context rather than explicit exclusions.

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