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

Annotations already declare readOnly/idempotent/non-destructive/open-world, and the description adds substantial behavior beyond them: $0.02 per call, x402/MPP payment flow, an optional Bearer access-key mode that auto-pays and returns data, a free first call per day, and validation-before-charge. The remaining weakness is that the two return modes are described inconsistently ('returns the paid x402 request' vs 'returns the data'), so an agent cannot fully predict what actually comes back without an access key.

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 use-case trigger is correctly front-loaded, but the body is dense with operational onboarding, including a long key-purchase URL, and repeats itself ('Call that URL with an x402 or MPP client to get the data'). Pricing, auth modes, free-tier behavior, and validation could be tightened into a few clearly separated sentences instead of one run-on block.

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 paid, dual-mode tool with no output schema, the description covers the essentials an agent needs: cost, how payment works, the access-key shortcut, the free-first-call rule, and that invalid input is rejected pre-charge. It is slightly short on the actual return payload shape (record fields, pagination metadata) and on how paging interacts with billing.

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 description coverage is 100%, so every parameter (since, status, country, page, limit) already carries its own meaning, format, bounds, and the 400-day window. The description adds no parameter-level guidance such as how to choose status values or how paging interacts with the paid per-call charge, so it sits at the baseline.

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 concrete verb and resource: it returns legal-entity (LEI) records 'created, lapsed' since a date, framed for KYB/LEI register maintenance. That distinguishes it from point-lookup siblings like company_lei or company_lei_batch, though it never names those siblings explicitly. The purpose survives the payment boilerplate around it, but the boilerplate dilutes the opening.

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 opening clause gives a clear trigger condition: 'Use when you keep a KYB/LEI register and need what changed since your last run.' It does not cover when NOT to use it or route to the sibling alternatives (company_lei for single-entity lookups, sanctions_changes for a different register domain), so the exclusions and alternative mapping are left to inference.

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