Sellers

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower, yet the description still adds real behavior: "Torob returns all offers at once; limit slices them" reveals a fetch-then-truncate pattern, and it defines `unreliable` (bait/stale) and clarifies that `stats` are computed over usable offers only. It stops short of stating rate limits, auth needs, or failure modes for a bad product id.

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?

Purpose and ordering are front-loaded in the first sentence, followed by usage, a field glossary, and parameter notes — a sensible order with no filler. It is dense and runs long, but the field glossary is doing necessary work because there is no output schema, so almost every clause earns its place.

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 explain the return shape, and it does so field by field (price in Toman, null when out of stock, score/votes, flags, updated, stats with min/median/max and price_spread_pct). Combined with 100% parameter documentation and 8 params, an agent has everything needed to call and interpret this tool correctly.

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 and the schema already carries city, limit, min_score and the boolean filters. The description still adds meaning the schema cannot: the default hiding of unreliable offers, that `city` selects shops serving that city, and above all that `limit` slices a full upstream result set rather than constraining the query.

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 first sentence states a specific resource (every online shop offer for a product) with an explicit ordering rule (cheapest first) and the extra data attached (trust, warranty, installment, delivery). An agent immediately knows this is a per-product offer listing. It does not, however, name or differentiate itself from close siblings such as tb_offers, tb_cheapest or tb_compare, so the reader must infer the boundary.

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?

"Use to pick where to buy" gives an implied use case (buy-decision comparison), which is genuine guidance but not a when/when-not rule. No alternative tool is named for the adjacent jobs (single cheapest price, side-by-side compare, deal checking) despite several siblings clearly overlapping. Usage is inferable rather than specified.

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