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

Beyond the annotations, the description discloses important behavioral traits: zero-slippage oracle pricing, transactionBase64 returned only after builder-side simulation passes, approval gating conditions, and the signer boundary where hosted builders never receive keypair bytes and value-moving results must be finalized locally. This adds substantial context beyond destructiveHint=true.

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 and action guardrails are front-loaded, followed by structured SAP execution guidance. It is somewhat verbose and repeats boilerplate that also appears in the schema description, but the information is organized and earned by the tool's payment and signing complexity.

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 tool is complex: paid, unsigned, value-moving, and Adrena-specific. The description covers intent, pricing, routing, signer boundary, simulation gating, and approval safety. Minor gaps remain around what to do if safeToApprove is false beyond not finalizing, but the output schema and annotations cover much of the remaining context.

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 schema already documents all five parameters including enums for fromToken/toToken, human-readable units, owner base58, and raw minAmountOut. The description adds no additional per-parameter meaning, so the baseline score of 3 applies.

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 states a specific verb and resource: 'Build an unsigned transaction to swap tokens through an Adrena pool.' It also distinguishes this tool from generic swap tools by calling out zero-slippage oracle pricing and the unsigned transaction builder nature, which separates it from siblings like jupiter_swap and other sap_adrena_build_* tools.

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?

Clear usage context is provided: this is a paid hosted builder, estimate before paying, finalize locally, and only show approval when safeToApprove=true and approvalBlocked=false. It also includes practical routing guidance for x402 versus sap_payments_call_paid_tool. However, it does not explicitly name sibling alternatives or explain when to prefer this over Jupiter/Orca swap tools.

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