Skip to main content
Glama
Freight-Art

abapsmith

by Freight-Art
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Read ABAP runtime errors (ST22 short dumps)

abap_dumps
Read-onlyIdempotent

Retrieve ABAP runtime errors (ST22 short dumps) from the system dump repository. List recent dumps or show full details chapter by chapter to diagnose failures.

Instructions

Read ABAP runtime errors (ST22 short dumps) from the system's dump repository — not the exception text of a run this server just triggered. mode=list filters the dump feed; mode=show returns one dump, chapter by chapter. The feed reaches back 8 DAYS ONLY: an empty list means "no dumps in the last 8 days matching this filter", never "nothing failed". Copy key from a list row VERBATIM. show returns a summary (exception, short text, error analysis, how to correct, source line, top of the call stack, chapter index); section or chapters returns chapter text — where terminated, source extract, system fields, call stack, and nothing else unless the operator enabled more.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNolist: newest dump to include, YYYYMMDDHHMMSS. No page cursor exists; to page backwards, set to= the oldest timestamp already seen.
keyNoshow, required: key exactly as a list row printed it. Do not trim, re-encode or rebuild it — internal spaces are significant.
maxNolist: rows to request (default 20).
fromNolist: oldest dump to include, YYYYMMDDHHMMSS in the server's local time.
modeNo"list" (default) filters the dump feed; "show" returns one dump by key.
queryNolist: server-side FQL filter, e.g. and ( equals ( user , DEVELOPER ) , equals ( runtimeError , MESSAGE_TYPE_X ) ). Operator FIRST, then attribute, then the value, UNQUOTED. One and(...)/or(...) wrapper is mandatory even for a single predicate; max 2 levels deep. Validated locally before sending.
offsetNoshow: 1-based first line of the returned chapter text.
sectionNoshow: which chapter text to return instead of the default summary. "analysis" = short text, error analysis, how to correct, exception chain; "source" = where terminated + source extract; "stack" = call stack; "environment" = system/user/session fields; "all" = the full default set (where terminated, source extract, system fields, call stack). Alternative to chapters.
chaptersNoshow: comma-separated chapter NAMES, e.g. "kap7,kap8,kap11" — names, never the titles, which are translated. Alternative to section. Without either, show returns a summary; every chapter this dump has is listed in the response.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.6.25
    • changedInput schema / properties / chapters / description
      Previous value: -"show: comma-separated chapter NAMES, e.g. \"kap7,kap8,kap11\" — names, never the titles, which are translated. Default: where terminated, source extract, system fields, call stack. Every chapter this dump has is listed in the response."New value: +"show: comma-separated chapter NAMES, e.g. \"kap7,kap8,kap11\" — names, never the titles, which are translated. Alternative to section. Without either, show returns a summary; every chapter this dump has is listed in the response."
    • addedInput schema / properties / section
      Added value: +{
+  "description": "show: which chapter text to return instead of the default summary. \"analysis\" = short text, error analysis, how to correct, exception chain; \"source\" = where terminated + source extract; \"stack\" = call stack; \"environment\" = system/user/session fields; \"all\" = the full default set (where terminated, source extract, system fields, call stack). Alternative to chapters.",
+  "type": "string"
+}
  2. First observedv0.3.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior, and the description adds substantial operational context: 8-day feed retention, empty list semantics, verbatim key copying, and exactly what sections or chapters return. This goes well beyond the annotations without contradicting them.

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

Conciseness5/5

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

The description is dense but every sentence earns its place: purpose and scope first, followed by critical caveats, then mode/output details. It is long only because the tool's behavior is complex, and it avoids restating the tool name or echoing the schema for padding.

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

Completeness5/5

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

Given no output schema, the description sufficiently explains return values, list limitations, show summary contents, and chapter section behavior. With 9 parameters and complex filtering/paging semantics, this description provides the key operational warnings an agent needs to avoid misinterpretation.

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?

The input schema already covers 100% of parameters with detailed descriptions, so the baseline is 3. The description adds meaningful operational nuance such as the 8-day window, the chapter-name-versus-title rule, and the warning that an empty list does not mean nothing failed. This goes beyond the schema to improve correct invocation.

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?

The description clearly states it reads ABAP runtime errors (ST22 short dumps) from the system's dump repository, using a specific verb and resource. It also explicitly distinguishes itself from the exception text of a run this server just triggered, helping an agent avoid confusing it with run-related tools.

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?

The description gives clear context for when to use each mode, including list versus show, and emphasizes the 8-day retention window so an empty list is not misread. It does not explicitly name sibling alternatives or state when not to use the tool, but the behavior is well-scoped.

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