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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), and the description layers on the things annotations cannot: the matching cascade (exact → prefix → token → one typo → fuzzy), that results come in rank order rather than score order, that persons are appended after companies with node_type person and score null, and that connected_sources explains empty results. That is unusually rich disclosure of non-obvious behavior.

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 purpose, then query formats, then matching semantics, then return shape — a sensible order. The single dense paragraph and tangled clauses like 'the leading legal entity a name stands for first' cost it clarity, but almost every sentence carries non-redundant information.

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?

There is no output schema, so the description must describe returns — and it does: node_id, jurisdiction, status fields, register identifiers, node_type for person hits, null scores, and connected_sources on misses. For a two-parameter search tool this covers everything an agent needs to call it and interpret the response.

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; the description earns above that by naming the concrete identifier schemes (LEI, ISIN, BIC, register number) and the format variants (scheme-prefixed vs bare, spaces tolerated), plus what the name matcher actually does. The limit parameter is left entirely to the schema, which is fine given its explicit description, but means the description is not fully additive across both params.

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?

Opens with a specific verb+resource ('Find a company by name or identifier') and immediately constrains what counts as a query. It also positions itself in a workflow by noting hits carry the node_id that entity_risk_profile consumes, which separates it from the downstream detail tools. It stops short of naming a sibling it is *not* (e.g. screening_lookup or search_stonewake_docs), so it is clear but not fully differentiating.

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 concrete usage context: acceptable query shapes, that bare identifiers work with or without spaces, and that the tool should be used when the intent is a company lookup. Also explains the empty-result case (connected_sources reports registers searched) and the person-data behavior. No explicit when-not or named alternative is offered, so it is strong context without exclusions.

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