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

With no annotations provided, the description fully discloses crucial behaviors: receipts are on-chain and provable, verdictCount is self-reported/advisory, pricing plan is injected, the tool is stateless and non-custodial, and undated receipts are excluded from dated windows with a warning about under-charging. This is exemplary transparency that goes well beyond typical descriptions.

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 information-dense and each sentence contributes a distinct piece of context (on-chain receipts, self-reported verdicts, injected pricing, statelessness, window honesty). The structure is effective with a clear lead phrase 'USAGE → BILL' followed by supporting detail, though the heavy use of caps and parenthetical asides slightly hampers readability.

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?

Without an output schema, the description still covers the key output categories (split, charges, total), distinguishes provable vs self-reported components, and highlights the critical under-charging edge case. It doesn't provide an exhaustive output field list and leaves 'split by trust' somewhat vague, but overall it supplies enough context for agent decision-making.

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 60%, with descriptions for plan, receipts, and verdictCount. The description adds significant meaning for the undocumented toBlockTime/fromBlockTime parameters via the 'DATED window' and 'no on-chain block time' discussion, and clarifies that verdictCount is not chain-provable. However, it doesn't explicitly reference the time parameter names, relying on the concept of a dated window.

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 indicates this tool computes a bill from usage ('USAGE → BILL') and explicitly states the return value: 'the provable/self-reported split + itemized charges + total.' This distinguishes it from invoice creation or payment tools among the siblings. However, the arrow notation and pilot-specific jargon make the primary verb somewhat less direct.

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 explains the input provenance (receipts on-chain, verdictCount self-reported, plan injected) and the window-honesty edge case, which implies this tool is for metering usage from till_receipt data. Yet it never explicitly states when to use this over sibling tools like till_create_invoice or till_check_invoice, and gives no direct exclusions or alternative recommendations.

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