Skip to main content
Glama
fr0ster

mcp-abap-adt

by fr0ster
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

SearchObject

Search an ABAP repository by object name or wildcard pattern, optionally filtering by object type, to find objects or confirm existence.

Instructions

[read-only] Search ABAP repository by object name or wildcard pattern (e.g. 'Z*'). Answers: "find object X", "does X exist", "list objects matching...", "search for program/class/table by name". Supports all repository object types — optionally filter by type (PROG, CLAS, INTF, DEVC, TABL, DDLS, DTEL, FUGR, SRVD, SRVB, BDEF, DDLX, etc.).

Input Schema

TableJSON 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
maxResultsNo[read-only] Maximum number of results to return
object_nameYes[read-only] Object name or mask (e.g. 'MARA*')
object_typeNo[read-only] Optional ABAP object type (e.g. 'TABL', 'CLAS/OC')

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field 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"
+}
  2. First observed

TDQS

A4.1/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the disclosure burden; it does state '[read-only]' itself, which is real value. It says nothing about result truncation at maxResults, ordering, whether only identifiers or metadata are returned, or any rate/timeout behavior for large wildcard scans — notable gaps for a search tool with no annotation coverage.

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?

Front-loads the read-only marker, verb, resource, and wildcard syntax before elaborating on type filtering. The quoted user-intent list is slightly listy but every item maps to a distinct real use case, so little is wasted.

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 4-parameter, no-output-schema search tool, the description covers matching semantics, wildcard usage, scope (all repository types), and type filtering. The remaining gap is what the result payload actually contains beyond the detail enum, which is not explained anywhere.

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 goes further than the schema by enumerating concrete object_type codes (PROG, CLAS, INTF, DEVC, TABL, DDLS, DTEL, FUGR, SRVD, SRVB, BDEF, DDLX) where the schema only offers two examples. The detail and maxResults parameters are left to the schema, which handles them adequately.

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?

States a specific verb (search) and resource (ABAP repository object) plus the supported matching modes (name or wildcard like 'Z*'). The listed example queries — 'find object X', 'does X exist', 'list objects matching' — make it immediately distinguishable from retrieval siblings such as GetObjectInfo or GetTable, which fetch a known object rather than locate one.

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

Usage Guidelines4/5

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

Maps natural-language intents to this tool explicitly, which is effectively strong when-to-use guidance. It does not, however, contrast itself against nearby siblings like GetObjectsByType or GetObjectsList, leaving the agent to infer that this is the name-pattern search route.

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