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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds real behavioral context beyond that: sole proprietors are excluded from results, most small businesses have no LEI, and lookups work by either name or the 20-character LEI. It does not discuss pagination or partial-match behavior, but the coverage-limitation notes are genuinely useful.

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 trigger clause, then examples, accepted inputs, return fields, and exclusions. The examples are slightly redundant with the trigger sentence but each illustrates a distinct mode (name lookup, LEI lookup, status check), so they earn their place. No filler sentences.

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?

An output schema exists, so return fields need not be spelled out (though they are, briefly), and annotations cover safety. Between description, schema, and output schema, an agent has everything needed to select and call this tool correctly, including the exclusion boundaries.

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 all four parameters (lei, name, limit, country) are already documented with patterns, bounds, and defaults. The description only restates the name-vs-LEI either/or and the country-narrowing role, adding no syntax or format detail beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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 specific verb+resource ('look up the Legal Entity Identifier (LEI) of a company') and scopes it against siblings like lookup_company_registry and check_vat_number by describing exactly what is returned (LEI, legal name, status, registration number, renewal dates). An agent can distinguish this from a general registry or VAT lookup without opening the 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 concrete trigger examples ('what is the LEI of Siemens AG?', 'whose LEI is W38RGI023J3WT1HWRP32?') and explicit when-not conditions: no private persons, no companies without an LEI (most small businesses), and no financial/credit information. Both the positive trigger and the exclusion boundary are stated, which is exactly what routing requires.

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