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

Adds real behavior beyond the annotations: a hard cap of 20 results, a freshness window (only offers valid today), a geographic boundary, and an explicit statement that it does not sell, reserve or deliver. The read-only/idempotent profile is already covered by annotations, so no credit is lost there, but pagination/truncation behavior beyond "up to 20" is left unstated.

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?

Four short, front-loaded lines that each carry distinct information: return shape, freshness, examples, coverage limits. The telegraphic labels ("Cobertura:") are terse but readable; nothing is redundant.

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?

Output schema exists so return-value explanation is a bonus, not a requirement, and the description still covers return fields, freshness, geography and mutation scope. The one material hole is sibling disambiguation against `search_offers`, which the agent cannot infer from the description.

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?

With one parameter at 100% schema coverage the baseline is 3; the description earns an extra point by showing sample query strings ("ofertas de café", "cerveja em promoção"), which tells the agent the query is a free-form product phrase rather than a structured filter.

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 ("Busca ofertas vigentes") and even the return shape (up to 20 results with id, título, url). It does not, however, distinguish itself from the sibling `search_offers`, which by name alone appears to do the same thing — an ambiguity the description never resolves.

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 example queries and an explicit exclusion ("Cobertura: só Joinville/SC, Brasil; não serve para outras cidades"), which is a genuine when-not rule. It stops short of routing among siblings — `search_offers`, `find_cheapest`, `top_deals`, `compare_product` are never mentioned, so an agent has no signal for choosing between them.

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