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

Annotations already cover the safety profile (readOnly, idempotent, open-world), so the description earns credit for what it adds: that officers and filings are pulled in by default, which materially changes payload size, and that identifier routing happens automatically via check-digit validation. It stops short of noting that openWorldHint implies external registry calls with possible latency or rate 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?

Three dense sentences with no filler, front-loaded with the core action and identifier formats before the resolution rules and default payload behavior. Every clause carries information an agent needs.

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 single-entity read with no output schema, the description covers input forms, routing logic, and default response content well enough to call it confidently. The remaining gap is the undocumented max_filings parameter, which no other structured field explains.

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 only 40%: id and country are documented in the schema, but filings, officers, and max_filings carry no schema descriptions. The description partially compensates by restating that officers and filings are on by default and by expanding id formats beyond the schema, but it never explains what toggling those booleans off does or what max_filings controls.

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?

"Look up one company by its official identifier" gives a specific verb (look up) and a bounded resource (one company), which cleanly separates it from the sibling search_companies. It goes further by enumerating the accepted identifier schemes (SIREN, SIRET, organisasjonsnummer, Y-tunnus, CIK, ticker), so an agent knows exactly what constitutes a valid lookup key.

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 gives concrete operational context: country may be supplied separately or embedded as a prefix, and ambiguous ids are routed by check-digit validation. What it does not do is name the alternative explicitly (e.g., "use search_companies to resolve a name into an id first"), so the selection guidance against the sibling remains inferred rather than stated.

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