Skip to main content
Glama

CreateServiceDefinition

Creates an initial service definition exposing CDS views as an OData service; supports activation, custom source code, and batch-mode recording.

Instructions

Create a service definition that exposes CDS views as an OData service, in initial state. When activate is false and source_code is absent, recordable: in batch mode a call is recorded under the next number and answers with empty content; its answer is read by number after the batch ends.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "service_definition_name": "<service_definition_name>",
      "package_name": "<package_name>"
    },
    "name": "CreateServiceDefinition"
  }
}

Input Schema

NameRequiredDescriptionDefault
detailNoHow much of the answer to return: "terse" (default, the fields you need to act), "full" (the whole parse), "raw" (the document as ADT sent it).terse
activateNoActivate service definition after creation. Default: true.
descriptionNoService definition description. If not provided, service_definition_name will be used.
source_codeNoService definition source code (optional). If not provided, a minimal template will be created.
package_nameYesPackage name
master_languageNoOptional master/original language for the created object (e.g. "EN", "DE", "ZH"). Defaults to the session language (SAP_LANGUAGE) or EN.
transport_requestNoTransport request number, not a task. Required for transportable packages.
service_definition_nameYesService definition name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv16.0.0
    • addedInput schema / properties / detail
      Added value: +{
      +  "default": "terse",
      +  "description": "How much of the answer to return: \"terse\" (default, the fields you need to act), \"full\" (the whole parse), \"raw\" (the document as ADT sent it).",
      +  "enum": [
      +    "terse",
      +    "full",
      +    "raw"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / package_name / description
      Previous value: -"Package name (e.g., ZOK_LOCAL, $TMP for local objects)"New value: +"Package name"
    • changedInput schema / properties / service_definition_name / description
      Previous value: -"Service definition name (e.g., ZSD_MY_SERVICE). Must follow SAP naming conventions (start with Z or Y)."New value: +"Service definition name."
    • changedInput schema / properties / transport_request / description
      Previous value: -"Transport request number (e.g., E19K905635). Required for transportable packages."New value: +"Transport request number, not a task. Required for transportable packages."
  2. Changed1 schema field changedv8.1.0
    • addedInput schema / properties / master_language
      Added value: +{
      +  "description": "Optional master/original language for the created object (e.g. \"EN\", \"DE\", \"ZH\"). Defaults to the session language (SAP_LANGUAGE) or EN.",
      +  "type": "string"
      +}
  3. First observed

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries full burden. It usefully discloses that the object is created in initial state (inactive) and explains batch-mode recording semantics with empty responses, but omits permission requirements, failure modes, and the fact that activation is required afterwards.

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

Conciseness3/5

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

The purpose is front-loaded in one clear sentence, but the second sentence is dense and awkwardly phrased ('recordable: in batch mode a call is recorded under the next number and answers with empty content'), requiring re-reading. It is short overall but not optimally structured.

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?

For a mutation tool with eight parameters and no output schema, the description covers creation state and the notable batch edge case that an agent would otherwise miss. Remaining gaps (post-creation activation, transport handling) are partly covered by schema field descriptions.

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. The description goes beyond the schema by explaining the interaction between activate=false and absent source_code and the resulting batch recording behavior, which is meaningful parameter-level semantics not captured in individual field descriptions.

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

Purpose4/5

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

States a specific verb and resource (Create a service definition) and adds scope: exposes CDS views as an OData service, created in initial state. This distinguishes it from ActivateServiceDefinition and UpdateServiceDefinition by the 'initial state' qualifier, though it never names alternatives.

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

Usage Guidelines3/5

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

Provides a conditional usage note for the batch/recordable case when activate is false and source_code is absent. However, it gives no explicit guidance on when to choose this versus UpdateServiceDefinition or ActivateServiceDefinition, or on prerequisites such as transportable packages.

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