Skip to main content
Glama

RuntimeRunClass

Run an ABAP class implementing if_oo_adt_classrun and return its output. Set profile=true to capture a profiler trace.

Instructions

[runtime] Execute an ABAP class implementing if_oo_adt_classrun and return its output. Set profile=true to also capture a profiler trace: schedules the trace, runs the class under it, then searches the profiler feed for the id this run produced (bounded by max_trace_attempts/trace_retry_delay_ms). If the trace has not appeared within that bound, the run still answers success with output and profiler_id but no trace_id — poll RuntimeListProfilerTraceFiles or RuntimeAnalyzeProfilerTrace afterwards. No run_status or trace_requests_status field is returned — the client exposes no transport status for a run.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
profileNoWhen true, run with the profiler and search the profiler feed for the resulting traceId. Default false.
aggregateNo
sql_traceNo
amdp_traceNo
class_nameYesABAP class name to execute.
descriptionNoProfiler trace description (only used when profile=true).
all_db_eventsNo
explicit_on_offNo
with_rfc_tracingNo
all_dynpro_eventsNo
trace_lookup_urisNoAccepted for backward compatibility; no longer affects trace lookup. adt-clients 19 lists the profiler feed as one endpoint, optionally filtered by user — there is nowhere to put a URI.
max_trace_attemptsNoMax attempts to poll the profiler feed for the trace this run produced (default 5). Only used when profile=true.
all_procedural_unitsNo
max_time_for_tracingNo
trace_retry_delay_msNoDelay in ms between profiler-feed polling attempts (default 2000). Only used when profile=true.
max_size_for_trace_fileNo
all_misc_abap_statementsNo
all_system_kernel_eventsNo
all_internal_table_eventsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv16.0.0
    • changedInput schema / properties / max_trace_attempts / description
      Previous value: -"Max polling attempts to resolve traceId after execution (default 5). Only used when profile=true."New value: +"Max attempts to poll the profiler feed for the trace this run produced (default 5). Only used when profile=true."
    • changedInput schema / properties / profile / description
      Previous value: -"When true, run with the profiler and resolve the resulting traceId. Default false."New value: +"When true, run with the profiler and search the profiler feed for the resulting traceId. Default false."
    • changedInput schema / properties / trace_lookup_uris / description
      Previous value: -"Additional URIs to consult when resolving the trace (advanced, profile=true)."New value: +"Accepted for backward compatibility; no longer affects trace lookup. adt-clients 19 lists the profiler feed as one endpoint, optionally filtered by user — there is nowhere to put a URI."
    • changedInput schema / properties / trace_retry_delay_ms / description
      Previous value: -"Delay in ms between trace polling attempts (default 2000). Only used when profile=true."New value: +"Delay in ms between profiler-feed polling attempts (default 2000). Only used when profile=true."
  2. Addedv6.7.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does so unusually well: it discloses the trace scheduling/polling flow, the bounded retry via max_trace_attempts/trace_retry_delay_ms, the partial-success semantics (success with output and profiler_id but no trace_id), and the absence of run_status/trace_requests_status fields. It omits permission/auth requirements, which is the remaining gap.

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-loaded with the core action, then dense but purposeful detail on the profiling branch and its failure mode. Every sentence carries information; the long parenthetical clauses are justified by real edge-case semantics rather than filler.

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

Completeness3/5

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

For a 19-parameter tool with no output schema, the description covers the important profiling semantics and return-shape caveats well, but the many undocumented boolean trace flags make it incomplete for fully informed invocation. Adequate but with clear gaps.

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

Parameters3/5

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

Schema coverage is only 32% across 19 parameters, so the description must compensate. It explains profile, max_trace_attempts, and trace_retry_delay_ms within the flow narrative, but leaves roughly a dozen trace-configuration parameters (aggregate, sql_trace, amdp_trace, all_*_events, explicit_on_off, etc.) undocumented in both schema and description.

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: execute an ABAP class implementing if_oo_adt_classrun and return its output. Clear what the tool does and its precondition on the class interface. It does not differentiate from the sibling RuntimeRunClassWithProfiling, which appears to overlap, so it falls short of a 5.

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?

Explicitly tells the agent when to set profile=true, what that flow does, and which tools to use afterwards if the trace is missing (RuntimeListProfilerTraceFiles or RuntimeAnalyzeProfilerTrace). Good routing to follow-up tools, though it never addresses the overlap with the dedicated profiling sibling tool.

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