PostCode Check

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

Annotations already declare readOnly/idempotent/closed-world, so the bar is lower, and the description still adds real value: it promises a complete listing of 'every' country (i.e. no pagination/no filtering) and enumerates the returned attributes. It doesn't address caching or whether the list is stable over time, which is minor for a static reference set.

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?

A single dense sentence plus a short safety clause and endpoint reference; the payload contents are front-loaded and every clause carries information an agent can use (field list, read-only, REST parity). No filler.

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 zero params, rich annotations, and an output schema handling return values, the description covers everything an agent needs: what it returns, that it's exhaustive, that it's safe, and where the same data lives in the REST API.

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?

Zero parameters, so per the baseline this scores 4. The schema and the empty properties block already make clear no input is required, and the description adds nothing that could mislead about arguments.

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?

Specific verb + resource ('List every supported country and territory') and it enumerates the exact payload fields (ISO code, English name, postal-code flag, format example, local code name). It is unmistakably distinguishable from the sibling validate_postcode.

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 static reference-lookup nature and 'Read-only' phrasing imply when to use it, and the REST equivalent (GET /v1/countries) gives a mental model. But it never states the relationship to the sibling — e.g. 'use this to discover valid country codes before calling validate_postcode' — nor any when-not condition.

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 adds substantial context beyond the annotations: the underlying pattern source (Google libaddressinput), an illustrative input/output transformation, and the explicit edge-case behavior for countries without postal codes (valid false, reason "no_postal_codes"). It also reinforces that this is a pure format check with no existence guarantee.

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 purpose and result shape are front-loaded, followed by the example, the limitation, and the edge case. It is dense and every sentence carries information, though the trailing reference to the equivalent REST endpoint is marginally useful for an MCP caller.

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 annotations covering safety/idempotency, full schema coverage, and an output schema, the remaining unknowns an agent would care about — normalization behavior, failure semantics, and non-postal-code countries — are all addressed. Nothing needed to invoke it correctly is missing.

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 the baseline is 3, but the description adds a concrete worked example (NL, "1234ab" → "1234 AB") that shows how the country parameter drives validation and how the code is normalized. This goes slightly beyond the schema's per-field examples.

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 states a specific verb and resource (check a postal code's format for a country) and explicitly describes the normalization output and its limits. It is clearly distinct from the only sibling, list_countries, which does not validate anything.

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 clearly scopes when this tool is appropriate — format checking only, not existence or deliverability — which tells an agent when not to rely on it. There is no real alternative tool to route to, so there is no explicit alternative sentence, but the use boundary is well established.

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