callFunction

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

The description goes well beyond the annotations (readOnlyHint=false, destructiveHint=false) by detailing side effects: it executes on the target system as the connected user, rolls back changes unless commit is set, warns that modules with internal commits cannot be rolled back, and states it is a writing tool refused in read-only mode. It also discloses input validation behavior and output structure, providing rich behavioral context beyond the annotations.

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 lengthy but well-structured, starting with a clear purpose, then mechanics, output details, validation, and finally safety. Every sentence adds useful information for a complex tool with 8 parameters. While it could be trimmed, the density of technical details is appropriate for a low-level function module caller in an ABAP environment.

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 all critical aspects an agent needs to invoke the tool correctly: how to specify the module (name), what happens with signature validation, output format (exporting/changing/tables, exceptions, row counts), side effects (rollback, commit, internal commits), and the restriction to read-only mode. Combined with a fully described input schema)Skiping nothing major is missing. The lack of an output schema is compensated by a detailed description of the return value structure.

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%, so the baseline for parameter semantics is 3. However, the description adds meaningful context that goes beyond the schema: it explains the role of commit (default rollback, override to keep changes) and clarifies that values are validated against the signature before sending. While dryRun, maxRows, keepClass, and snippetClass are not elaborated in the description, the schema descriptions for those parameters are already sufficient, so the description still adds value for the core parameters.

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 opens with a clear, specific statement: 'Call a function module with values and get what it returned, as data.' It identifies the exact resource (function module) and differentiates from sibling tools like callMethod by naming the resource type. The subsequent details about looking up the function group and generating the call reinforce the purpose.

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 explains what the tool does but never states when to use it over alternatives. It does not mention any exclusions, prerequisites, or comparisons to sibling tools such as callMethod, runClass, or runSnippet. The only contextual clue is the function module emphasis, which implies a use case but is not explicit.

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