sap_read_table

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

Even though readOnlyHint=true and destructiveHint=false already cover the safety profile, the description adds substantial operational behavior: auto-detection of table type, the table_type field in the response, columns_only=true returning metadata with no data, per-column cell_type and cell_id template for TableControls, and start_row pagination semantics. This goes well beyond what annotations alone provide.

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 runs ~120 words and is dense but every sentence earns its place: purpose, auto-detection behavior, table_type routing, columns_only mode, column filtering, and pagination. It is front-loaded with the core purpose and follows a logical order. It could be tightened slightly, but there is no fluff or repetition of schema content.

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?

With an output schema present and read-only annotations, the description covers most of what an agent needs: table type scope, mode switching, column selection, pagination, and next-step routing. The main completeness gap is the undocumented required table_id (where to get it) and max_rows semantics, which matter for correct invocation on a 5-parameter tool.

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?

With 0% schema description coverage, the description carries the full burden and does explain columns_only (schema discovery, cell_type/cell_id template), columns (CSV selection), and start_row (pagination) meaningfully. However, it never explains the required table_id parameter — where an agent obtains it or what identifies a table — nor does it clarify max_rows behavior. Missing the one required parameter is a significant 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?

The description opens with a specific verb+resource ('Read rows from a table on the current screen') and precisely scopes the target to two UI constructs: ALV grid and TableControl. This clearly distinguishes it from siblings like sap_read_field (single field), sap_read_list (list output), and sap_get_cell_info (individual cell), so an agent can select it correctly without inspecting schemas.

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 gives explicit context for when to use the tool: any table on the current screen, with the ALV-vs-TableControl distinction spelled out. It also routes the agent to the correct follow-up tools based on the returned table_type (sap_get_alv_toolbar vs sap_scroll_table_control). It stops short of explicitly naming alternatives NOT to use (e.g., sap_read_field), but the scoping is clear enough that exclusion is mostly implied.

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