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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as false. The description adds value by explaining the pricing model (x402 challenge), routing requirements, and signer boundary – details not captured in annotations. It does not contradict annotations; in fact, the readOnlyHint aligns with the 'read/discovery' intent stated in the description. The only minor gap is no mention of potential response size or pagination.

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 relatively concise at two sentences before the execution guidance block, but the SAP execution guidance adds substantial length. The structure is clear: first sentence states purpose, second lists return fields, then the routing/signer guidance. It could be slightly more concise by integrating the execution guidance more tightly, but it's well-organized and front-loaded.

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 has only 1 optional parameter, complete annotations, an output schema, and is a simple read operation, the description adequately covers all necessary context: purpose, return fields, pricing, routing, and security boundaries. No obvious gaps remain for an AI agent to select and invoke this tool 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 coverage is 100%, so the schema already documents the single optional 'symbol' parameter with its description. The description does not add extra meaning beyond what the schema provides – it mentions 'per-asset' implicitly but doesn't elaborate on the symbol filter's behavior (e.g., case sensitivity, wildcard support). Baseline 3 is appropriate when schema covers all params adequately.

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 tool fetches 'per-asset custody statistics' from the Adrena Data API and lists specific return fields (open interest, utilization, volume, fees). It distinguishes itself from sibling tools by focusing on a specific type of read operation (custody info) within the Adrena family.

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 explicit guidance on when to use this tool (read/discovery workflow) and detailed routing instructions: call sap_estimate_tool_cost first, then use sap_payments_call_paid_tool if needed. It also gives a crucial exclusion about the signer boundary (hosted reads never receive keypair bytes). This is exceptional guidance beyond what siblings provide.

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