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

Adds substantial context beyond the annotations: the result cache is only 24 hours (a real time limit that changes call strategy), reconciliation performs no signing/charging, and receipt/transaction details must be kept private. This is consistent with idempotentHint=true and destructiveHint=false; readOnlyHint=false is coherent because reconcile touches on-chain state, and the description explicitly bounds that side effect.

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?

Two dense sentences with no filler, and the hardest constraint (no new payment) lands early. The leading fragment 'For a buyer-held PRIVATE receipt ID...' reads slightly awkwardly as an opening and the cache TTL could be tighter, but nothing is wasted.

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 three params, no output schema, and low schema coverage, the description carries the burden well: it explains all three modes, the 24-hour result window, the no-charge guarantee, and the privacy requirement. The remaining gap is failure behavior — what status/result returns when the cache has expired or the receipt is unknown — which an agent would want before relying on the 24-hour boundary.

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 only 33% and the 'mode' enum has no per-value documentation, but the description compensates by mapping the three operations onto status/result/reconcile ('Check payment and delivery', 'reconcile... on-chain', 'retrieve the original result'). receipt_id and transaction_hash formats are already handled by schema patterns and the transaction_hash description; only the default and per-mode requirements are left implicit.

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?

States a specific verb (recover) plus resource (already purchased API output) and enumerates the three concrete operations: status/delivery check, on-chain reconciliation, and cached result retrieval. The opening phrase 'For a buyer-held PRIVATE receipt ID' implicitly separates it from locate_owned_receipt/find_owned_api (you already have the receipt), but no sibling is named, so differentiation is inferred rather than stated.

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?

Gives a clear precondition ('buyer-held PRIVATE receipt ID from a previous purchase') and a hard exclusion ('reconciliation can confirm EXISTING settlement only'), which tells the agent this is never a substitute for a purchase flow. However it never names kevaremesh_locate_owned_receipt or kevaremesh_find_owned_api as the path when no receipt_id exists, leaving that routing to inference.

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