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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral context: only currently valid offers are returned, results are paginated, coverage is limited to one city, and the default sort. It does not explain how the cursor expires or whether pagination totals are exposed, but that is a minor gap given annotations and an output schema.

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 lines, front-loaded with what is returned, then the sort semantics, examples, and scope limits. Minor redundancy between the description's sort list and the schema's identical sort description, but no filler.

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 6-parameter read tool with full schema coverage and an output schema, the description supplies the pieces that structured fields cannot: geographic coverage limits, the today-only offer window, and example phrasings. Only the omission of any sibling routing keeps it from being complete.

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 schema already documents market, sort, cursor, category, page_size and region. The description's sort enumeration largely restates the schema's own sort description and adds no format or edge-case guidance for cursor or region; baseline 3 is appropriate.

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 ("Mostra um mercado") and enumerates what comes back: endereços, destaques, categorias e ofertas paginadas. It is immediately distinguishable from search_offers or find_cheapest by its single-market scope, though it never explicitly names list_markets as the way to discover a slug/id.

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 invocation examples ("ofertas do Angeloni", "o que tem no Cooper") and a hard coverage exclusion — only Joinville/SC, not other cities. It also clarifies the tool is read-only ("não vende, não reserva nem entrega"), which is a form of when-not guidance, but it never routes the agent to a sibling tool for out-of-scope requests.

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