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

Beyond annotations, the description adds key behavioral context: the tool builds but does NOT broadcast, it returns an unsigned transaction for local signing, hosted builders never receive keypair bytes, and value-moving results are finalized locally. This enhances the readOnlyHint=false/destructiveHint=true picture without contradicting it.

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 sentence is compact, front-loaded, and specific, with the no-broadcast caveat placed immediately after the action. The SAP MCP execution guidance block restates some of the signing/finalization point, causing slight redundancy, but it remains compact and relevant.

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 a rich output schema and full parameter-schema coverage, the description covers the critical operational context: unsigned transaction, local signing, payment/estimate-first routing, signer boundary, and the next-step execute tool. An agent has enough information to decide whether and how to invoke it correctly.

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 the parameters are fully documented there. The description adds a useful behavioral note that token symbols are resolved to canonical mints, but it does not need to explain fromSymbol/toSymbol/fromAmount/wallet semantics beyond what the input schema already says, matching the baseline-3 rule for high schema coverage.

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: 'One-call Sunrise swap intent' that resolves token symbols to canonical mints, fetches a quote with user wallets, and returns unsignedTransaction, quoteId, routeName, and providerRequestId. It also clearly states the transaction is NOT broadcast and names sap_sunrise_execute_quote as the follow-up, which differentiates it from the execute/get/resolve siblings.

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?

It gives concrete guidance: sign locally, execute with sap_sunrise_execute_quote, estimate cost first, and use the paid-tool routing path when x402 is not supported natively. It does not explicitly say when to prefer this over sap_sunrise_get_quote or other quote-only siblings, so the when-not guidance is not fully explicit.

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