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

The description extensively documents behavior: it distinguishes honest states (published_value, documented_absence, located_unverified), explains pagination, format options, and that values come with source and as-of. Annotations only provide readOnlyHint=true; the description adds crucial context beyond that.

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?

The description is front-loaded with the core purpose and then details. It is somewhat lengthy but necessary given the complexity of the tool (multiple parameters, states, formats). Every sentence adds value except perhaps the exhaustive list of jurisdictions, which could be truncated with an ellipsis.

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?

The description covers input parameters, states, pagination, and formats. With no output schema, it explains the kinds of values returned. It could be more explicit about the overall response structure (e.g., 'returns an array of category objects'), but the pagination hints and state descriptions compensate.

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% with descriptions, but the tool description adds significant value: it lists all activities and jurisdictions, explains pagination parameters (limit, offset), clarifies format differences, and provides examples for category lookup. This goes well beyond the schema descriptions.

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 clearly states that the tool retrieves published licence requirements (capital, local presence, etc.) for canonical activities in African jurisdictions. It distinguishes from sibling tools (cross_border_rules, list_licensed, map_license) by focusing on requirements to hold a licence, not on cross-border rules or lists of licensed entities.

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 explains how to key by activity, jurisdiction, or exact category ID, and specifies default vs. full format. It does not explicitly state when to use alternatives, but the scope is clear and the sibling tool names indicate distinct purposes.

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