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

Annotations already declare this as a read-only, idempotent, closed-world lookup, so the safety profile is covered. The description adds genuinely non-obvious behavior: results with a high fieldCount are generic fallbacks, so callers should constrain maxFieldCount to get codes specific enough to align on. It still doesn't describe the shape or volume of the returned codes.

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, no filler, with the use case front-loaded and the parameter advice second. Every sentence earns its place.

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 one-optional-parameter read-only lookup, the definition covers the scenario and the parameter tradeoff, which is most of what an agent needs. However, with no output schema and no statement of what comes back (a list of codes? with what identifying fields?), the agent cannot predict the response it must map against.

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 0% and the single parameter has no description of its own, so the description must carry it — and it does, explaining that high fieldCount yields generic fallback codes and recommending a starting value of 10. The relationship between maxFieldCount and per-code fieldCount is inferable but not stated outright, keeping it short of a 5.

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 names the concrete scenario (mapping fields from SAP, another ERP, or a supplier feed onto Open Footprint), which combined with the title makes clear this surfaces semantic codes for mapping. It stops short of a clean verb+resource statement of what the tool actually returns, and it never distinguishes itself from siblings like ofp_semantic_code or semantic_query.

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 an explicit triggering condition ("Use this when mapping fields from...") plus operational advice on setting maxFieldCount starting around 10. It lacks any when-not guidance or pointer to the closely named siblings, which is the main gap for an agent choosing among ofp_semantic_code, semantic_query, and semantic_templates.

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