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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds real behavioral context beyond them: aggregates span the whole group while the member list is capped by limit, results carry data_as_of, depth/direct_parent_lei/consolidation % are per-member, and fund-management link types are filtered out. That is materially more than the structured fields provide.

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-loaded with the value proposition and the input contract, then examples, then exclusions and metadata. Dense but each sentence carries information; the example questions and the return-field enumeration are slightly padded but earn their place for a tool with no output 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?

With no output schema, the description must describe the return shape, and it does: aggregates (member_count, jurisdiction_count, by_jurisdiction), per-member fields (depth, direct_parent_lei, consolidation %, jurisdiction, LEI status), the limit cap, and data_as_of freshness. Given the tool's complexity and 2-param surface, nothing needed to invoke or interpret it correctly 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 coverage is 100%, so the baseline is 3, but the description adds meaning: the input may be a LEI of ANY member or a company name (a subsidiary match still resolves to the whole group), and it clarifies that limit caps the listing while counts and by_jurisdiction always cover the whole group. This is genuinely beyond the schema text, though not exhaustive on resolution failure behavior.

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 precise verb+resource: returns every entity in a corporate group built on GLEIF Level 2 relationship records. It explicitly distinguishes itself from the sibling lei_hierarchy_tree and frames the exact unit of aggregation (ultimate accounting-consolidation parent and all descendants). An agent can tell it apart from lei_hierarchy_tree, get_lei_relationships, and entity_profile without opening any schema.

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?

Gives explicit when-to-use (large groups, whole-group queries), names the alternative tool to prefer over (lei_hierarchy_tree, because it walks one node at a time and truncates at 150), and lists concrete example questions. It also states an exclusion (fund-management links are NOT ownership and are not included), which is exactly the kind of boundary an agent needs.

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