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

Goes well beyond the readOnly/idempotent/openWorld annotations: it discloses pricing ($0.05 per call, free when nothing is found or on failure), the jurisdiction-specific coverage of each source, that people are returned by name and role only, and that notes describe what a register doesn't publish. This is substantive operational context an agent could not get from structured fields.

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-loads the purpose then enumerates sources and cost. A single dense sentence covering sources is packed but each clause carries coverage information; the pricing and limitation sentences are useful. Slightly overstuffed but no wasted filler.

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 read-only tool with no output schema, the description covers sources, coverage, cost, and output nature (people by name and role). It could say more about the shape of returned records, but it is largely complete enough to call correctly.

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?

Only one parameter, and the schema documents it at 100% coverage, including accepted id formats (fr:, gb:, lei:, etc.). The description adds no additional meaning about the company argument, so the 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 and scope: who owns a company and what it owns, with the data sources enumerated (GLEIF, 10-K Exhibit 21, Wikidata, UK PSC). An agent can tell it retrieves ownership/subsidiary relations rather than a company profile. It does not explicitly name sibling tools like companies_get or companies_search, so it stops short of full sibling differentiation.

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 implied by the purpose (call it to get parents/subsidiaries/controllers), but there is no explicit when-to-use vs when-not guidance, no reference to alternatives such as companies_get for general company data, and no stated prerequisites. Reasonable inference required.

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