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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is handled; the description goes further by disclosing the price model ("$0.03 per `company-report`") and the provenance guarantee ("Every value links to the official record it came from"), which materially affects trust and cost decisions. It omits failure behaviour — what happens on no match or ambiguous names — so it lands at 4 rather than 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?

The lead sentence is well front-loaded, but the middle is a single sprawling run-on that packs a full jurisdictional inventory into comma-separated clauses, which is hard to scan and partly redundant with the `include` enum. The isolated price line is efficient, but overall the geography dump could be compressed or moved to the schema.

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?

For a multi-jurisdiction lookup with four parameters and no output schema, the description covers what data comes back per country, that values are sourced, and what it costs — enough for an agent to call it confidently. Missing pieces are the response shape (single object vs sections), not-found/disambiguation behaviour, and any latency or quota expectations.

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 100% schema coverage, the schema already documents query, country, include and maxYears, so the baseline is 3. The description does add real meaning by mapping jurisdiction to populated fields (e.g. UK current directors and PSC, Poland KRS board/proxies/bankruptcy entries, US banks FDIC), which helps an agent set `country` and `include` intelligently, but it never explains how those semantics attach to the parameters explicitly.

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 opening sentence gives a concrete framing ("who is this company and what are its numbers?") and then enumerates the exact data returned: legal name, LEI, registration number, status, financials, SEC filings, directors/PSC, KRS entries, FDIC record. That is far more specific than a restatement of the name. It stops short of 5 because it never distinguishes itself from near-neighbours like counterparty_check or sanctions_screening, leaving overlap to inference.

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?

"Built for AI agents doing research, KYB or due diligence, and for people who want a quick, sourced company profile" gives audience and intent, so the general context is implied. There are no when-not conditions, no prerequisites, and no routing to sibling tools (e.g. when to prefer sanctions_screening or vat_iban_check), so an agent must still guess at boundaries.

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