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

Annotations already provide readOnlyHint and openWorldHint, but the description adds substantial behavioral context: there is no retroactive history, the observation window is gap-free by construction, GDPR removes officers/shareholders/PESEL, free text is discarded except for inferred dates flagged date_source_inferee, and a non-existent KRS returns the same shape as a quiet company. These are exactly the kinds of non-obvious behaviors an agent needs to interpret results correctly.

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 description is dense but front-loaded: the first sentence states the core purpose and event taxonomy, and every subsequent clause adds an operational caveat or distinguishing behavior with no filler. Although long, the length is justified by the tool's many non-obvious behaviors, and the key warning about KRS existence is clearly highlighted with IMPORTANT.

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?

Given the tool complexity and the presence of an output schema, the description covers what matters: event scope, date semantics, existence behavior, GDPR constraints, payment/auth modes, and the deciding court or authority fields. Nothing an agent needs to decide whether to call this tool or interpret its result is missing.

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 baseline is 3; the schema already documents krs, api_key, and x_payment. The description adds meaningful semantic context beyond the schema: the krs parameter's relation to existence checking (non-existent numbers still return aucun_evenement), the difference between api_key and x_payment payment paths, and the $0.02 x402 pricing. That additional guidance lifts it above baseline.

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?

The description opens with a specific verb and resource — "Registry EVENTS of a Polish company" — and enumerates the exact event types served (liquidation, bankruptcy, restructuring, mergers, filings, etc.). It distinguishes itself from country-specific sibling tools by tying itself to the Polish KRS bulletin and even names get_european_company_profile as the existence-checking alternative.

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?

The description explicitly tells the agent when not to rely on this endpoint for existence checks: "this endpoint does NOT check that the KRS number exists," and it names get_european_company_profile (pays=PL) as the way to settle existence with a 404. It also gives concrete payment usage: omit x_payment to receive a quote, or use api_key for prepaid credits.

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