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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the safety profile is covered. The description adds genuine behavioral detail beyond that: input normalization (bare digits zero-padded and prefixed with "RA") and the fact that it returns a register's name, website and jurisdictions. It does not discuss failure modes for unknown codes, which keeps it at 4 rather than 5.

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 purpose, then example, then normalization, then the sibling caveat — a sensible ordering. It is slightly repetitive, restating the "585" -> "RA000585" normalization in both the description and the schema and mentioning the `registration_authority` linkage twice, but no sentence is wasted.

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 return values — and it does (register name, website, jurisdiction(s)). Combined with the single fully documented parameter, the safety annotations and the explicit sibling routing, an agent has everything needed to call this correctly.

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?

Only one parameter and schema coverage is 100%, so the schema already carries the syntax. The description nonetheless adds semantic context the schema lacks: what the code represents (the register that assigned the entity's `registered_as` id) and the concrete RA000585 example. The normalization rule is repeated from the schema, which is mildly redundant but not harmful.

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?

Names a specific verb ("Decode") and resource ("GLEIF Registration Authority (RA) code") and enumerates exactly what comes back: the register's name, website and jurisdiction(s). The Companies House example and the tie to the `registration_authority` field on LEI records make it unmistakable versus siblings like get_lei or bic_to_lei.

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?

Explicitly routes the agent: get_lei already decodes this inline as registration_authority_decoded, so call this tool only when you have a bare code from elsewhere. That is a clear when-to-use, when-not-to-use, and named alternative in one sentence.

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