Start ABAP Debug Listener

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

Annotations are minimal (readOnly=false, idempotent=false, destructive=false), so the description carries the disclosure burden — and delivers. It flags a protocol change ('the old attach to a terminal/session id had no counterpart in the ADT protocol'), explains the trap-and-freeze side effect on the user's work process, notes sessionId is a server-local handle that 'does not survive a server restart,' and documents 409 conflict behavior including automatic clearing of crashed listeners. Nothing contradicts the annotations; the destructive take_over path is explicitly disclosed.

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

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

Well-structured with labeled sections (workflow, args, returns, error handling) and the core purpose front-loaded in the first sentence. The workflow and error-handling sections earn their length for a multi-step lifecycle tool, though the Args section partially duplicates a schema that already covers all parameters at 100%.

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

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

With no output schema, the description documents the return shape explicitly — '{ sessionId, state: LISTENING, user, mode, message }' — and explains sessionId semantics. It covers both error paths (409 conflict with take_over recovery; single-session constraint), the mandatory detach step, and the prerequisite of running code as the target user before sap_debug_wait. Nothing essential is missing for a tool with this complexity.

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

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

Schema coverage is 100% and the schema descriptions are already rich — mode's 'reference-only, not verified on this system' caveat and user's 'freezes THEIR session — only do it with their knowledge' warning are in the schema itself. The description's Args section mostly echoes this, adding only the historical context that 'terminal_id' is gone and restating defaults. Baseline 3 is correct because the schema does the heavy lifting.

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

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

First sentence uses a specific verb and resource: 'Open a debug session handle and confirm this server may listen for a user's execution.' It explicitly differentiates from the nearest sibling — 'sap_debug_wait is what actually registers the listener and blocks' — and the numbered workflow positions this call as step 1 of a 6-step debug lifecycle. An agent can distinguish it from sap_debug_wait, sap_debug_detach, and the other debug-family tools without opening their schemas.

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

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

Provides an explicit numbered workflow (attach → set breakpoint → execute as user → wait → inspect → detach) that states exactly when this call runs and in what order. It names the alternative explicitly, gives conditional guidance for conflicts ('Re-run with take_over=true to seize it'), and warns 'One debug session at a time: detach the current one first.' Usage context and exclusions are both explicit.

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