CreateProgram

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

With no annotations, the description carries the full burden. It does disclose two real traits: the object is created inactive ('initial state') and in batch mode it returns empty content whose answer is fetched later by number. It omits authorization needs, what happens if the program already exists, and confirmation that transport_request is needed for transportable 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?

Purpose is front-loaded in the first sentence and the second sentence adds the lifecycle state. The batch-mode sentence is dense and slightly jargon-heavy ('recorded under the next number'), but it carries non-obvious information and is not padding.

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 8-parameter creation tool with no output schema and no annotations, the description covers what is created, its initial state, and the batch-mode return contract. What remains missing is the activation follow-up and error/duplicate handling, which is a modest but real 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 description coverage is 100% with enums documented for detail and program_type, so the schema already carries parameter meaning. The description adds nothing param-specific (e.g., no guidance on master_language vs application defaults), 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?

States a specific verb and resource ('Create a new ABAP program (report)') and adds a scope qualifier ('creates the program object in initial state'), which implicitly separates it from UpdateProgram and from CreateProgramUnitTest. It does not name a sibling explicitly, so an agent must infer the Create/Update/Activate family relationships.

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?

Usage is only implied from the verb - there is no statement of when to use this versus CreateProgramUnitTest, UpdateProgram, or how it relates to ActivateProgram (only the hint 'initial state'). The batch-mode clause describes recording behavior rather than tool selection, though it does tell the agent this call can be deferred.

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