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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), so the bar is lower, and the description still adds real behavior: no model is involved, no probability is given, the exact verdict vocabulary, and the fallback resolution logic for line slugs via resolved_to. It stops short of describing coverage/edge behavior when 30 or 90 days of checks are not met, beyond the NOT ENOUGH DATA mention.

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 core purpose and outputs are front-loaded, and the middle expands into the comparison rules. It is one very dense paragraph with some parenthetical asides ('said as low_period', 'for example ...') that slow parsing, though almost every clause carries operational information.

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 no output schema, the description must carry the return semantics, and it does: the three verdict values, the buy-or-wait verdict, per-line basis, and resolved_to. It leaves out pagination/format details and the exact meaning of the near-low band, which are minor for a read-only evaluator.

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 100%, so the baseline is 3, but the description adds meaning the schema lacks: a product_slug may be a line slug (e.g. 'samsung-galaxy-ring') naming the newest model, and the tool resolves to the newest on-sale model with an explanation in resolved_to. It does not further explain retailer or price_usd beyond the schema, but that is unnecessary.

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?

Starts with a specific verb+resource ('Whether a price offered for one product is a good deal') and immediately enumerates the three possible outputs. It explicitly names the sibling should_i_buy and distinguishes itself by taking an offered price, so an agent can separate it from siblings without opening a schema.

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 reference to 'the same written rules as should_i_buy' clearly frames the relationship and implies the selection condition (this tool evaluates a specific offered price; should_i_buy does not). It does not, however, state explicit when-not conditions or spell out the choice between this and the price-related siblings like get_price_history.

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