grir_differences

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

With no annotations, the description carries the full burden, and it does disclose real behavior: the source table (EKBE), the mismatch-only filter, the key_date default of today, and the hard cap of 1000 rows on top. It does not state that the operation is read-only, whether top truncates silently, or what permissions/company-code scoping are needed, so the behavioral picture is only partly filled in.

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 dense sentences, front-loaded with what is computed and what is returned, followed by the optional filters and limits. No filler and nothing that restates the title.

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?

An output schema exists, so return values need not be described, and the description covers source, grain, filter, defaults and limits. The remaining gap is that the single required parameter (company_code) is undocumented, which matters for a SAP-domain tool that will otherwise fail on invocation.

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 0%, so the description must compensate, and it does for four of five parameters: it supplies the key_date format (YYYY-MM-DD), clarifies that the default is today (the schema's empty-string default is otherwise meaningless), and adds the 1000 cap on top that the schema does not express. The required company_code is never explained anywhere, which is the one real gap.

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 resource and scope: GR/IR differences per PO item, GR vs IR quantity and value, mismatches only, sourced from EKBE. That is far more informative than the sibling names (open_items_ageing, trial_balance_by_period) require, but it never explicitly contrasts itself with those adjacent reconciliation tools.

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?

"only mismatches" implicitly tells the agent this is a reconciliation-exception tool rather than a full ledger dump, which is genuine usage guidance. However, there is no explicit when-to-use/when-not statement, no prerequisites (SAP login/company code selection), and no named alternative for the full-population case.

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