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

Beyond the annotations, the description discloses important runtime behavior: transactionBase64 is returned only after builder-side RPC simulation passes, approval is gated by safeToApprove and approvalBlocked, and hosted builders never receive keypair bytes so value-moving results must be finalized locally. This meaningfully exceeds what readOnlyHint/destructiveHint alone communicate and does not contradict the annotations.

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?

The core behavior is front-loaded in three tight sentences, and the execution guidance is separated and labeled clearly. It is concise and well-structured, though the SAP guidance block is somewhat generic and is also echoed inside the schema description.

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?

The description covers payment routing, simulation gating, safe-approval handling, and signer-boundary behavior, giving an agent the critical workflow context. Return structure is likely handled by the output schema, and edge cases like missing stop-loss orders are not discussed, but no essential call-blocking context appears to be missing.

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 description coverage is 100% and each parameter has a basic explanation: owner is the base58 wallet key, principalToken is the asset, and side is the position side. The free-text description adds no parameter-level detail beyond the schema, so the baseline of 3 is appropriate.

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?

The description clearly states the verb and resource: 'Build an unsigned transaction to cancel stop loss on an Adrena position.' This is specific enough to distinguish the action from setting, trailing, or take-profit variants, though it does not explicitly name sibling tools such as sap_adrena_build_set_stop_loss or sap_adrena_build_cancel_take_profit.

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?

The SAP MCP execution guidance gives concrete operational context: estimate cost first via sap_estimate_tool_cost, route through sap_payments_call_paid_tool when x402 is unsupported, and finalize locally. It also specifies that approval should only be shown when safeToApprove=true and approvalBlocked=false, and that finalize must not be called otherwise. It does not contrast this with alternative Adrena position-management tools, but the core usage context is clear.

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