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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds real value beyond them: it is deterministic and derived from merchant-declared data, freshness is bounded by max_age_seconds, and it enumerates the exclusions (shipping classes, cost formulas, duties, taxes on shipping). It stops short of saying what happens when the confirmation is older than max_age_seconds (error vs. stale result), which is the one behavioral gap.

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?

Dense but front-loaded: the computation is defined first, then exclusions, then parameter guidance, then the authority caveat. Every sentence carries information, though the parenthetical free-shipping explanation is packed tightly enough to slow reading.

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 six parameters, no output schema, and thin schema descriptions, the description carries most of the burden and does so well by describing both what the result includes and explicitly what it excludes. The missing piece is the return shape and default values, which the agent must infer.

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 17% (only destination is documented), so the description must compensate, and it does explain variation_id, live, and the max_age_seconds window. However, p2209_id is never described, quantity is only implied via 'item price x quantity', and no defaults are given for quantity, live, or max_age_seconds.

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 and resource ('deterministic estimate ... item price x quantity plus the shipping options the store declares for the destination') and explains exactly what the computation covers. The closing line 'The checkout is the only authority' implicitly separates it from the verify_* siblings that do authoritative checks.

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 concrete usage conditions: pass variation_id for variable products, use live=true to read the merchant now, and the result is only valid within max_age_seconds of the last confirmation. It does not explicitly say when to prefer verify_offer or verify_basket over this estimate, but the 'checkout is the only authority' caveat supplies that context.

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