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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds real behavior beyond that: expired deals are excluded, results are newest-first at 25 per page, prices are in BRL with old price and discount %, content is Brazilian Portuguese, and query is a literal substring match rather than semantic. Minor gaps (total result counts, what happens when nothing matches) remain.

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 scope, ordering, and page size are front-loaded, followed by result contents, language constraint, matching caveat, and price usage. Almost every sentence carries actionable content, though the single dense paragraph packs several distinct topics (result shape, language, matching behavior, price params) that would scan better as separate sentences.

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?

An output schema exists, so result-field enumeration is arguably redundant, but the description still covers what an agent needs: freshness filtering, ordering, page size, currency, language of the corpus, substring matching semantics, and price filtering. The only real omissions are explicit behavior for zero results and relationship to sibling lookup tools.

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 coverage is 83% (baseline 3), but the description adds genuine semantics beyond the schema: `query` is a literal substring of title or description, and min/max price map to named budget scenarios ("até R$ 3.000", "entre R$ 100 e R$ 200"). It also implies store/category slugs come from list_stores and list_categories, reinforcing the schema descriptions.

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 ("Search active (not expired) deals on Pechincha.ai") plus scope details: newest-first ordering, 25 per page, and the fields each result carries. This clearly distinguishes it from get_deal, get_product, and list_stores without needing to open their schemas.

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 guidance: search in Portuguese because content is pt-BR, prefer short terms, and use max_price for budgets and min_price for floors/ranges. It also warns that accessory matches pollute results ("notebook" returns backpacks) and that titles should be checked. It stops short of naming explicit alternative tools for narrower lookups (e.g., get_deal for a known deal), so it's strong but not fully routing-aware.

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