run_sap_report

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 that output is written to files under Downloads/SAP reports, that the response is only a path/columns/preview, the 5000-row cap, the ~55 s completion budget, and that no popups are handled. It omits auth expectations (sap_login) and what occurs on timeout or failed report selection.

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 most important facts (what it does, where output goes, ask-user-first warning) are front-loaded, and the param notes follow in a compact order. The telegraphic fragment style and inline JSON example make it dense, but nearly every clause carries 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?

For a five-parameter tool with an output schema and nested selections object, the description covers execution semantics, output location, row limits and the safety precondition, so an agent can call it correctly. Residual gaps are the undocumented `folder` parameter and error/timeout behavior, which matter because a 55 s cap is stated but its failure mode is not.

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%, yet the description explains the two most complex parameters in depth: variant as a saved variant and selections with a concrete example showing single values, multi-value lists, and low/high ranges in internal formats, plus the max_rows ceiling of 5000. The `folder` parameter and the exact form of `report` (tcode vs program name) remain unexplained.

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 states a specific verb and resource ("Run an SAP GUI report (tcode or program) and save its output") plus the output artifact (ALV to Excel, classic lists to text). It is clearly distinguishable from siblings like find_sap_reports (discovery), sap_report_info (metadata) and read_sap_table (raw table reads).

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?

It gives concrete execution guidance: use a saved variant as the easiest path, use selections to override it, and ask the user first for any report that may post, change or send. It does not explicitly name sibling tools or say when to prefer find_sap_reports/sap_report_info instead, so routing is implied rather than spelled out.

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