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

Annotations only cover readOnlyHint and openWorldHint, and the description adds substantial context beyond them: ~12 s latency with a recommended 30 s timeout, a $0.005 USDC charge per successful call via x402 across three chains, and the explicit guarantee that failed calls are not charged. It also discloses result-shape behavior (best match plus up to 5 alternatives, parent or the reporting-exception reason, only the first 10 children).

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 identity and input form are front-loaded in the first clause, followed by returned fields, provenance, and then operational facts (latency, timeout, price). It is dense but nearly every clause carries information; the field enumeration is somewhat long given an output schema already exists.

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-parameter, read-only lookup with an output schema, the description covers source, latency/timeout, cost and payment path, and partial-result semantics, which is everything an agent needs to call it correctly. The only redundancy is re-listing return fields that the output schema already documents, and the absence of any pointer to the closest sibling tools.

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?

With one parameter at 100% schema coverage the baseline is 3, but the description adds meaning the schema does not: that a name query returns a best match plus up to 5 alternatives, and that a 20-character LEI is the exact-match form. That directly informs how an agent should interpret results and whether to refine q.

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 states a specific verb and resource ('Legal entity lookup in GLEIF') and pins the scope to the GLEIF Global LEI Index, plus the two accepted input forms (LEI or name). It is clear enough to distinguish from generic registry tools by source, but it never names a sibling (e.g. company_registry, uk_company, entities) that an agent might confuse it with.

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 only implied: KYC/LEI resolution is signaled by the kycSummary field and the 'direct and ultimate parent' output, but there is no explicit when-to-use or when-not-to-use statement relative to the many company-registry siblings. The operational guidance given (12 s typical, allow a 30 s timeout) is about invocation mechanics rather than tool selection.

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