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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely non-derivable context: the upstream register and its operator, what normalization the response performs, and a per-address price of $0.002, which is important cost information before a 50-item batch call. It stops short of disclosing no-match handling or rate limits.

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 core operation, then return shape, then audience, then price — a sensible order with no wasted sentences. The 'Built for AI agents doing real estate, logistics, KYC/KYB…' clause is slightly promotional, but it does carry use-case signal.

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 does a fair job sketching the response, and with zero required parameters it should explain what happens when none are supplied and how the optional inputs combine. Those calling-mode and error-behavior gaps are the main missing pieces for a 7-parameter, multi-mode lookup.

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 100% and all seven parameters are individually documented there, so the baseline is 3. The description corroborates the `include` sections by listing the same return facets (address, building, coordinates), but it adds nothing about the mutual exclusivity or precedence of `addresses` vs `postcode`/`houseNumber` vs `bagIds` — the one semantic point the schema leaves ambiguous.

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 uses a specific verb pair ('checks and geocodes') on a specific resource ('Dutch addresses against the BAG'), names the authoritative source (Kadaster/PDOK), and enumerates the return payload (postcode, BAG ids, WGS84/RD coordinates, building attributes). No sibling tool covers Dutch addresses, so the agent can identify this uniquely without consulting the schema.

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?

It gives audience/use-case context (real estate, logistics, KYC/KYB, insurance, address-list cleaning) but never frames this as a when-to-use against alternatives and never states how to choose between the three input modes (batch `addresses`, `postcode`+`houseNumber`(+range), or `bagIds`). Usage is implied rather than instructed.

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