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

Annotations only declare readOnly/idempotent/openWorld; the description adds the material operational facts an agent needs: the cost (0.08 USDC via x402 or 40 credits of a Factline API key) and the free quota (first 5 paid calls per day need no payment or key). It also previews the response shape (best address per metric plus full report per address), which annotations cannot convey.

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 the use condition, then output contents, then input format, then pricing — a sensible order with no filler. The metric enumeration is long but each item is informative; a slight trim would make it tighter.

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 paid, no-output-schema tool, it covers trigger, inputs, cost, free tier, and what comes back, which is nearly everything an agent needs. Minor gaps remain around failure modes (invalid addresses, exceeding 5, missing key without free quota left).

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%, so both parameters are already documented, and the description's 'addresses separated by ;' merely restates the schema. It does reinforce the 2–5 cardinality constraint, but adds no format or edge-case detail (e.g. what happens with a non-Dutch or invalid postcode) 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?

States a specific verb and resource ('Compare Dutch addresses') plus the exact scope: 2 to 5 addresses, side-by-side on a named list of metrics with a best-per-metric verdict. The comparison framing plus the 2–5 range distinguishes it from single-address siblings like nl_home_report or nl_address_lookup without needing to name them.

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?

'Use when the user is choosing between 2 to 5 Dutch addresses' gives an explicit triggering condition, and the 2–5 bound implicitly excludes single-address and bulk use cases. It does not name the sibling to use instead for one address or for 6+ addresses, so the routing is implied rather than spelled out.

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