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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, yet the description still adds concrete behavior: a hard cap of 20 results per call, offset/next_offset paging, and a total count alongside each hit's city, category and page URL. It doesn't mention empty-result behavior or ranking order, which keeps it from a 5.

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?

Front-loaded with the core purpose and concrete example queries, then the filter list, then the return shape. The trailing Polish sentence is a short bilingual echo rather than a full translation, so waste is minimal, though it does partially repeat earlier content.

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?

Return values needn't be spelled out given an output schema exists, and safety is covered by annotations; what remains – query syntax, facet vocabulary, result cap and paging – is all present. All parameters are optional, which lets the agent browse, and the description gives enough scaffolding to do that sensibly.

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 100%, so a baseline 3 would apply, but the description earns more by clarifying that category accepts either a slug or a Polish word and pointing to list_categories, and that country can be an ISO code or a Polish/English name. It also frames limit/offset as a paging pair. Minor gap: no guidance on combining zero filters versus a full filter set.

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?

A specific verb (search) applied to a precisely bounded resource: Polish-run businesses outside Poland listed on samiswoi.app. The example queries ("Polish plumber in London", "polska księgowa w Dublinie") make the scope instantly legible and distinguish it from sibling get_company (single record) and list_categories/list_countries (facets).

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?

Explicitly tells the agent how to build a query – filter by country/city/category/name phrase – and routes to list_categories for valid category slugs. It also explains paging via offset/next_offset. It stops short of stating when NOT to use it (e.g. when a specific business is already known and get_company should be used), so it's clear context rather than full when/when-not guidance.

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