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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, but the description adds crucial non-schema behavior: this is a paid endpoint at $0.001 USDC per call via x402 on Base mainnet, which the agent must know before invoking. It also warns that figures include levies and surcharges (e.g. Ghana's NHIL and GETFund), so the agent won't mistake them for bare statutory rates; it does not state rate recency or error behavior for unsupported countries, keeping it below 5.

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?

Front-loaded with coverage and concrete country/rate pairs that let an agent verify relevance at a glance, then use cases, then commercial terms. The enumerated country examples are slightly longer than strictly necessary, but they earn their place by demonstrating the dataset's granularity.

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 no output schema, the description still conveys what comes back (standard rates plus notes on levies and surcharges) and how coverage is bounded (49 countries, CFA franc zone). Missing only the as-of date of the rates and how unsupported country codes are handled, which matter for a tax-reference tool.

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 parameter already documents comma-separated 2-letter ISO codes and the all-49 default. The description's "filter by one or more ISO country codes" only restates that, adding no format or edge-case detail, so the baseline 3 applies.

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?

States a specific resource and scope: "Standard VAT and sales tax rates for 49 African countries," then grounds it with concrete examples (South Africa 15%, Nigeria 7.5%, Kenya 16%). This clearly distinguishes it from the rate-adjacent siblings such as exchange_rates and africa_central_bank_rates, which cover currency and policy rates rather than consumption taxes.

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 explicit use contexts (pricing, invoicing, quotes, cross-border e-commerce in Africa) and explains the filtering mode, so an agent knows when the tool fits. It stops short of naming an alternative or stating exclusions, so a 4 rather than a 5.

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