generate_rap_skeleton

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

With no annotations, the description carries the full burden. It clearly states it does NOT write to SAP and requires human approval, which are critical behavioral traits. It does not mention any side effects or destructive actions, which is appropriate for a code-generation step.

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 sentences with no wasted words: the step number, action, what is generated, what is not done, and the approval gate are all present and front-loaded.

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?

Given the tool's complexity (generates multiple code artifacts) and no output schema, the description covers the essential components (CDS view, Behavior Definition, etc.) and the key constraint (no writes). It could be slightly more explicit about the return format, but is still fairly complete.

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% with good descriptions for each parameter. The description adds context by linking analysis_json to analyze_module_pool, but does not provide additional semantic depth beyond the schema defaults.

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 it generates a full RAP migration plan as ABAP code strings, identifying it as Step 2 and distinguishing it from siblings like analyze_module_pool (Step 1) and write_abap_object (actually writes to SAP).

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 explicitly says when to use it (Step 2 after analysis) and that human approval is needed before writing. It implies when not to use through step context but lacks explicit exclusion statements.

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