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

Adds genuinely useful behavior beyond the annotations: cheapest-first ordering, a hard no-overspend guarantee, and dry_run=true previewing without mutating. However, 'Idempotent on purchase_id' directly contradicts the annotation idempotentHint=false, and idempotency is exactly the property an agent relies on when deciding whether a retry with the same purchase_id is safe — this conflict is safety-relevant and undermines the rest of the disclosure.

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?

Three tight sentences with the allocation rule and budget constraint front-loaded, followed by the caller profile and then the idempotency/dry-run notes. No filler; every clause conveys a distinct constraint.

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?

An output schema exists, so return values need no explanation, and the description covers allocation strategy, budget semantics, preview mode, and use case. The residual gaps are the undefined 'buyer' parameter and the unresolvable idempotency conflict with the annotations.

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 description coverage is 0%, so the description carries the burden and mostly does: it defines budget_minor's semantics (exact cost must fit inside, never overspends), purchase_id's role (idempotency key), and dry_run's effect (preview without mutating). Only 'buyer' is left undefined — the agent cannot tell whether it is an account ID, address, or display name.

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+resource (money-denominated offset purchase) and the exact allocation rule: retire the maximum cheapest-first verified mass whose exact cost fits inside budget_minor. The 'money-denominated' framing and 'exact cost fits inside budget_minor (never overspends)' cleanly separates it from the sibling buy_offset, which is presumably mass-denominated.

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 selection condition — 'Built for callers whose restoration obligation is a currency amount — e.g. a revenue share accrued in a ledger' — which tells the agent when this tool applies versus a quantity-based purchase. It stops short of naming buy_offset explicitly as the alternative to use when the obligation is expressed in mass/tonnes.

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