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

Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description discloses that the tool returns an unsigned transaction, never receives keypair bytes, and requires local finalization when signing is needed. These are meaningful operational facts that affect how an agent should handle the result. It does not enumerate failure modes or on-chain side effects, but for a builder the signing boundary is the most important behavior.

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 first sentence is an excellent front-loaded summary, but the appended 'SAP MCP execution guidance' block is verbose and duplicates the same guidance found inside the input schema description. The content is useful, but it could be tighter and less repetitive.

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?

For a five-parameter builder with an output schema and annotations, the description covers the essential points: what it builds, the raw return format, payment routing, and the signer boundary. It is complete enough for an agent to invoke it correctly, though it leaves the meaning of the trader subaccount/PDA index parameters to the schema.

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%, so per the baseline this dimension does not require the description to compensate. The description itself adds no parameter-level detail beyond what the schema provides; fields like traderPdaIndex and traderSubaccountIndex have descriptions in the schema, albeit thin ones.

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 opens with a specific verb and resource: 'Build an unsigned cancel stop loss transaction for Phoenix,' which clearly identifies what this tool does and distinguishes it from siblings like sap_phoenix_build_place_stop_loss and sap_phoenix_build_cancel_all. It also states the key output, transactionBase64, so an agent knows exactly what to expect.

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 description gives clear operational context: this is a paid, hosted, unsigned transaction builder, with explicit ordering ('estimate first, then pay/build') and a fallback routing instruction through sap_payments_call_paid_tool when x402 is not supported. It does not, however, state when the agent should choose this tool over sibling Phoenix builders (e.g., cancel_all vs cancel_stop_loss), so it stops short of full exclusion guidance.

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