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

Annotations already declare readOnlyHint=true, but the description adds a non-obvious behavioral trait: 'A null company_count means the job-corpus pass has not run for that name — it is NOT a measured zero.' This prevents a serious misinterpretation of a returned field. Since read-only safety is already covered by annotations, this extra semantics is meaningful and goes beyond what annotations provide.

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 carry the full message: the first states the tool's purpose and data model, the second covers the special scope filter and the null caveat. The critical null interpretation is placed at the end, but the most decision-relevant information (scope=horizontal behavior) is near the front. Every clause earns its place, though the second sentence is denser than necessary.

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?

With 7 parameters, no output schema, and only readOnlyHint as annotation, the description must compensate for missing structured context. It explains the core filters (scope, kind, jurisdiction) and even one output field (company_count), but it omits guidance on q, pagination, and the overall return shape. For a browsing tool this is adequate but not fully complete, leaving an agent to infer how to construct a basic query beyond the explained filters.

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 only 14% (only context has a description), so the description must compensate. It does so by explaining scope=horizontal with a specific use case, listing the supported kind values (regulation/statute/accreditation/regulator-guidance), and naming jurisdiction as a filter. However, it leaves q, page, and limit without explanation, which are also part of the schema, so the compensation is partial.

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 opens with 'Browse the laws, statutes and accreditations the catalog tracks' – a specific verb and resource that clearly identifies the tool's domain. It further characterizes records by their joins to countries, regions, and industries, which distinguishes it from sibling find_* tools focused on those entities themselves. However, it does not explicitly name a sibling alternative (e.g., get_regulation), so differentiation is implicit rather than explicit.

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 description gives a concrete usage scenario: 'Filter by scope=horizontal to get the regimes that reach a provider with NO industry tag at all, which is the question tags alone cannot answer.' This tells an agent when to use a specific filter, but it does not contrast the tool against alternatives like find_regions or get_regulation, so overall when-to-use guidance is partial.

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