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

Annotations already set readOnlyHint=false and destructiveHint=false; the description adds valuable context: it is a paid builder ('Builder fee applies'), requires a local-signer workflow, and stresses 'value-moving results must be finalized locally when signing is required.' It also discloses private-mode defaults and gasless mode, providing nuance beyond the raw annotation flags.

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 description is organized into three purposeful paragraphs: main purpose and features, follow-up workflow, and SAP MCP execution guidance. The first sentence is an immediate TL;DR, and every subsequent sentence contributes distinct information without redundancy. The length is appropriate for the tool's 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?

Given the tool's complexity (20 parameters, output schema, annotations), the description covers intent, pricing, routing, signer boundary, and follow-up steps. It does not explicitly mention that authToken is required for private transfers (though the schema does) or describe the return shape (covered by output schema). Overall, it is quite complete for a large tool, with only minor gaps.

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?

With 100% schema description coverage, the baseline is 3. The description goes beyond the schema by stating default values for private mode (minDelayMs=0, maxDelayMs=0, split=1) and explaining the intended use of base/ephemeral source/destination. The schema also contains a valuable legacy/vault size warning, but the description itself adds meaningful semantics around defaults and mode behavior.

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 SPL token transfer (public or private) through an Ephemeral Rollup.' This clearly distinguishes the tool from siblings like spl-token_transfer by emphasizing the Ephemeral Rollup and unsigned nature. It also lists key capabilities (delayed settlement, split transfers, gasless mode) that set it apart.

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 provides clear context: this builds unsigned transfers and explicitly directs the subsequent workflow (sap_preview_transaction, sap_sign_transaction, sap_submit_signed_transaction, or sap_payments_finalize_transaction). It also includes SAP MCP execution guidance (estimate first, use sap_payments_call_paid_tool when needed). However, it does not explicitly name when not to use this tool versus alternatives like spl-token_transfer, so it stops short of full exclusions.

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