Skip to main content
Glama
kts982

MCP SAP GUI Server

by kts982
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

sap_set_batch_fields

Fill multiple SAP GUI form fields, table cells, and dropdowns in one call instead of setting them one by one, returning success and failure counts.

Instructions

Fill in multiple input fields at once (dict of field_id to value).

Use this to fill a form or selection screen in one call — more efficient than repeated sap_set_field calls. Table-control cells work too: take the cell_id template of each column from sap_read_table(columns_only=true) and replace {row}. A dropdown (cmb) takes an entry's key or text, as in sap_set_field.

The result gives counts; results lists only the fields that did NOT succeed (all of them with verbose=true).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fieldsYesDict mapping field_id -> value.
verboseNoList every field in `results`, not only the failures.
validateNoPress Enter after setting fields and return status-bar feedback. Skipped when no fields were actually set.
skip_readonlyNoSilently skip fields whose element reports Changeable == False instead of counting them as failures.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.4.0
    • addedInput schema / properties / verbose
      Added value: +{
+  "default": false,
+  "description": "List every field in `results`, not only the failures.",
+  "type": "boolean"
+}
  2. Changed3 schema fields changedv0.2.2
    • addedInput schema / properties / fields / description
      Added value: +"Dict mapping field_id -> value."
    • addedInput schema / properties / skip_readonly / description
      Added value: +"Silently skip fields whose element reports\nChangeable == False instead of counting them as failures."
    • addedInput schema / properties / validate / description
      Added value: +"Press Enter after setting fields and return status-bar\nfeedback. Skipped when no fields were actually set."
  3. First observedv0.2.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation profile is covered. The description adds genuinely useful behavior beyond that: dropdown values accept an entry's key or text, table cells use a {row}-substituted template, and results contains only failures unless verbose=true. It stops short of describing failure/partial-application semantics or whether a failed field leaves the screen partially filled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short, front-loaded blocks: what it does, when to use it / special cases, and what comes back. Every sentence carries information, though the second paragraph packs several distinct rules (table cells, dropdowns) that could be segmented for faster scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't document return shape, yet it still does so briefly. Combined with 100% schema coverage and the cell_id template guidance, an agent has enough to invoke correctly. The only soft spot is that it never says where general field_ids come from for non-table fields (e.g. sap_read_field / sap_get_screen_elements), leaving the discovery path for the primary input unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description earns credit above it by explaining the shape and construction of the `fields` dict (field_id -> value, cell_id templates with {row}) and clarifying that `verbose` expands `results` to all fields rather than only failures. The untyped `additionalProperties: true` dict is the case where prose was most needed, and it is supplied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource and scope: 'Fill in multiple input fields at once (dict of field_id to value)', which immediately distinguishes it from the single-field sibling sap_set_field. It also pre-empts confusion by noting table-control cells and dropdowns are covered, so an agent knows the blast radius of this tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use it ('fill a form or selection screen in one call') and names the alternative it replaces ('more efficient than repeated sap_set_field calls'). It further routes the agent to sap_read_table(columns_only=true) to obtain the cell_id template, so the prerequisite step is prescribed rather than inferred.

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

Deploy Server

Other Tools