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

Annotations only convey read/write and idempotency hints. The description adds crucial non-obvious behavior: the exact credit cost, the mandatory preparation step, the private auth requirement, and that a new requestId triggers a new billable operation. This aligns with idempotentHint=true and goes well beyond the structured annotations.

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 dense, front-loaded sentences cover purpose, cost, prerequisites, and recovery semantics with no filler. The most important scope and exclusion information appears first, and every sentence adds operational value.

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 paid, preparation-dependent tool with a nested input schema and an output schema, the description is complete: it explains what the tool does, how much it costs, what must happen before calling it, what auth is required, and how to avoid duplicate billing. Remaining return-format details are covered by the output schema and 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?

The schema documents requestId and maxPriceMicroUsd, but the core `input` object lacks a top-level description. The description compensates by clarifying the comparison scope (up to 50 offers), unit compatibility classes, and no-currency-conversion rule, and by linking requestId reuse to recovery. It still leaves the interpretation of the `reference` sub-object mostly to the schema, so it is not a 5.

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 states a specific verb and resource: compare up to 50 explicit pack prices using exact arithmetic across compatible mass, volume, or count units. The 'no currency conversion' qualifier further distinguishes this unit-price comparison from money-conversion or pricing tools.

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 gives strong operational guidance: use agent_utilities_prepare first, requires existing credits, requires a private Authorization header, and explains recovery semantics and billing consequences of new requestIds. It does not explicitly name an alternative tool or say 'use this instead of X for Y', so it stops just short of a 5.

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