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

The annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real value beyond that with the caveat that codes carried by many fields are generic classifications and alignment to them asserts less than it appears — useful interpretive context. It still says nothing about what is returned or how many results to expect, which matters because there is no output schema.

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?

Two sentences, front-loaded with the usage trigger, and no filler. The second sentence is terse to the point of being cryptic ('asserts less than it appears'), but it does carry a substantive caution rather than padding.

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?

Scored against a one-parameter, read-only lookup with full annotation coverage and full schema description coverage, the description supplies the usage trigger plus the one non-obvious caveat about generic classifications. The main remaining gap — return shape — is partly offset by that caveat, and the directional wording is already penalized under purpose clarity.

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% and the single `code` parameter is documented with a concrete O-DEF example, so the schema carries the semantics. The description refers obliquely to 'a source-system field' and to codes without adding format, validation, or resolution rules beyond the schema. Baseline 3 is appropriate.

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 title promises 'fields for a semantic code' (code in, fields out), but the description frames it in the opposite direction: 'you have a source-system field and need to find where it belongs.' The required parameter is a code, so the description leaves the lookup direction ambiguous and an agent cannot tell with certainty whether it resolves code→fields or field→code.

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?

There is a genuine use-case trigger ('when you have a source-system field'), which is more than nothing. But it never names alternatives such as ofp_semantics, semantic_query, or ofp_search_entities, and gives no condition for choosing this tool over them or any precondition for obtaining a valid O-DEF code.

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