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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is the null-when-not-read or nothing-found condition and the scope of what the scraper covers (per-weekday hours, PL/EN/DE offer names, clients matched against KRS). That is genuine behavioral context beyond the annotations, though it doesn't discuss staleness or coverage limits.

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?

Two sentences, front-loaded with the resource and then the keying/null semantics. The category list is long but each item earns its place by telling the agent what it will actually receive.

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 does the work of explaining the return shape by enumerating fact categories and the null case, which is enough to call correctly. Minor gaps remain around ambiguity when only a name is supplied and how fresh the scraped data is.

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 three parameters are already documented; the description only restates the KRS/NIP keying and adds that sole proprietors with a public profile can be reached via NIP. That is a marginal addition over the schema, so baseline 3 applies.

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 resource (facts scraped from the company's own website) and enumerates the concrete fact categories, which cleanly separates it from the many registry-oriented siblings like get_company or get_company_public_contracts. The 'read from the company's own website' framing makes the distinction unmistakable.

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?

Usage is only implied by the data source ('website') and by the note that it is keyed by KRS/NIP and returns null when the site has not been read. It never says when to prefer this over get_company or other siblings, nor when the name-based fallback should be used. Adequate but leaves routing to inference.

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