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

Despite strong annotations (read-only, non-destructive, open-world), the description adds substantial behavioral context: the tree is capped at ~25 nodes, extra subsidiaries appear as an 'and N more' note, failing hierarchy hops are noted rather than fatal, and results are self-reported public-record data that should be verified. These details inform the agent about edge cases and data reliability beyond the structured annotations.

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 long but every sentence earns its place: it covers the tool's core behavior, algorithm, edge cases, data caveats, and differentiation from a sibling. The most important information is front-loaded, and the structure follows a logical flow from what it does, to how it works, to limitations and verification advice.

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 complex tree-building tool with no output schema, the description is remarkably complete. It explains the resolution flow, the ultimate-parent-and-descend approach, the returned fields (LEI, jurisdiction, status), how the queried entity is marked, the node cap, and the self-reporting limitation. An agent has enough context to invoke the tool correctly and interpret its results appropriately.

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 100%, so both 'company' and 'lei' are already documented fully in the input schema. The description repeats the name-or-LEI option and notes that LEI overrides name search, but this is also present in the schema. It adds no meaningful semantic detail beyond what the schema already conveys, so the baseline score of 3 is appropriate.

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 ('One-call FULL corporate-ownership tree') and immediately identifies the data source (GLEIF). It clearly distinguishes itself from resolve_entity, which returns only an ultimate parent and count, while this tool returns the actual subsidiary list/tree. This leaves no ambiguity about what the tool does or how it differs from a near-named sibling.

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 states when to use this tool ('for M&A, diligence, and counterparty mapping') and contrasts it with resolve_entity, which returns less information. It also explains the input alternatives (company name or 20-character LEI) and the key caveat that coverage is limited to self-reported relationships. This gives sufficient routing guidance without needing to inspect sibling tool schemas.

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