Afriset Fintech

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

Beyond annotations (readOnlyHint), the description discloses error handling (unknown facet errors), state types (published_rule, documented_absence, located_unverified), pagination behavior, and union scope expansion. It also clarifies that no FX rates are returned, adding significant safety context.

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 main purpose and structure. It uses headings, lists, and precise language. Despite length, every sentence adds value—no fluff given the tool's complexity.

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 complex tool with 9 parameters, multiple enums, and no output schema, the description covers filters, formats, states, error handling, pagination, and union scopes comprehensively. It leaves no major gaps for safe invocation.

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 descriptions cover all 9 parameters, but the tool description adds meaning: it explains direction filter logic ('both' matches any direction), facet format, format effects, and union scope interpretation, going well beyond the schema alone.

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 the tool provides cross-border money-movement rules for African markets, with a specific verb ('rulebook: what money may move') and resource distinction. It explicitly separates itself from siblings via domain (rules vs. licenses/maps) and states 'RULES, NOT RATES' to avoid confusion.

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 provides extensive filtering options and explains when to use different output formats (summary/full/compare). However, it does not explicitly contrast with sibling tools or state when not to use this tool, leaving some ambiguity about alternative selection.

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

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

Beyond the readOnlyHint annotation, the description discloses detailed behavioral traits: each entry carries source and as-of date, per-category coverage block with ingestion statuses, explanations for empty slices, default summary format that fits widest slice, and full format with pagination. This is comprehensive and adds significant value beyond annotations.

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 provides a structured list of activities and jurisdictions. While verbose, each sentence adds unique information. Could be slightly more concise, but the detail is valuable.

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 explains output characteristics (source, as-of, coverage blocks, pagination) despite the absence of an output schema. It covers default and full formats and how missing data is reported. Some specifics about row structure are omitted, but it is sufficiently complete for an LLM to understand the tool's behavior.

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 parameter descriptions, and the tool description adds context such as listing example activity values, all jurisdiction codes, union scopes (WAEMU, CEMAC), and default behaviors for limit and format. This enriches the schema information meaningfully.

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 the tool lists licensed/authorized entities for specific fintech activities in African jurisdictions from official regulator registers. It provides a comprehensive list of activities and 42 countries, distinguishing it from sibling tools like cross_border_rules, map_license, and requirements which serve different purposes.

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 implicitly indicates when to use the tool (when needing licensed provider data for specified activities and jurisdictions), but it does not explicitly compare with sibling tools or state when not to use it. It lacks guidance on selecting between alternatives.

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

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

Annotations indicate readOnlyHint=true, and the description reinforces a read-only mapping behavior ('normalization'). It adds context about the cross-country equivalence concept, but does not contradict annotations.

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?

Single sentence with illustrative examples. Front-loaded with the core purpose, no unnecessary words.

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?

Given 3 parameters with full schema coverage, no output schema, and simple data flow, the description adequately conveys the mapping logic and scope. Lacks return value details, which is acceptable without output schema.

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 clear descriptions for all three parameters. The description adds examples of canonical activities and jurisdictions, but does not significantly extend beyond the schema.

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 the tool maps canonical activities to local license categories across jurisdictions, with specific examples (Nigeria MMO ≈ Ghana DEMI). It uses a specific verb 'normalize' and uniquely identifies the resource, distinguishing it from sibling tools like cross_border_rules.

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 implies when to use (finding equivalent licenses across jurisdictions) and provides illustrative examples, but does not explicitly state when not to use or name alternatives. It gives clear context without exclusions.

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

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.