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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds value by disclosing the pass criteria and the fact that it returns findings plus a signed result, which annotations do not say. It stops short of describing what a 'finding' contains or how mismatches are reported, and the 64-character tx_hash format is left to the schema. This is adequate but not rich behavioral context.

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?

It opens with the core verb phrase and follows with the criteria, so the important content is front-loaded. The closing sentence 'Reads the ledger only' is a useful scoping constraint rather than filler. It is dense but fits in two compact sentences.

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 read-only tool whose annotations are complete, this covers purpose, criteria, and return shape, which is close to sufficient. The remaining gaps are the undocumented nested attestation object, the absence of any default or recommended network, and vagueness about what 'findings' a caller receives. It should say more about those than it does.

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 67%, so most parameters are already documented in the schema, including tx_hash format and the network enum. The description adds meaning for the attestation by tying it to the safepay_check_payment output, but it gives no guidance on choosing stellar:pubnet versus stellar:testnet, which is the one enum an agent must set correctly. Baseline 3 fits because the schema carries the weight.

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 names a specific verb and resource: it reads a Stellar transaction from Horizon and compares it against a SafePay precheck attestation. The comparison criteria (succeeded, approved payee, USDC, amount cap, validity window) sharpen the purpose. It does not, however, distinguish itself from the sibling safepay_verify, which an agent could easily confuse with this tool.

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 usage flow is implied rather than stated: the attestation parameter is described as 'the precheck attestation safepay_check_payment returned,' which tells the agent to run the check first. There is no explicit statement of when to use this versus safepay_verify, and no guidance on network selection or on what to do when verification fails.

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