lookup_uk_postcodeAddresses for a full UK postcode such as NW2 7JW (rate limited upstream). A partial postcode (only the outward part, e.g. NW2) is refused.
| Name | Required | Description | Default |
|---|---|---|---|
| postcode | Yes | UK postcode, e.g. NW2 7JW. |
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | ||
| addresses | Yes | ||
| suggestions | Yes | Possible postcodes when the one given is incomplete. |
Changes observed during successful MCP inspections.
Output schema / properties / addresses / items / properties / county / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]Output schema / properties / addresses / items / properties / county / typeAdded value: +[
+ "string",
+ "null"
+]Output schema / properties / addresses / items / properties / line_1 / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]Output schema / properties / addresses / items / properties / line_1 / typeAdded value: +[
+ "string",
+ "null"
+]Output schema / properties / addresses / items / properties / line_2 / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]Output schema / properties / addresses / items / properties / line_2 / typeAdded value: +[
+ "string",
+ "null"
+]Output schema / properties / addresses / items / properties / post_town / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]Output schema / properties / addresses / items / properties / post_town / typeAdded value: +[
+ "string",
+ "null"
+]Output schema / properties / addresses / items / properties / postcode / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]Output schema / properties / addresses / items / properties / postcode / typeAdded value: +[
+ "string",
+ "null"
+]Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "properties": {
+ "addresses": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "county": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "label": {
+ "type": "string"
+ },
+ "line_1": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "line_2": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "post_town": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "postcode": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ }
+ },
+ "required": [
+ "label",
+ "line_1",
+ "line_2",
+ "post_town",
+ "county",
+ "postcode"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "status": {
+ "type": "string"
+ },
+ "suggestions": {
+ "description": "Possible postcodes when the one given is incomplete.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "status",
+ "addresses",
+ "suggestions"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only/open-world semantics, so the description's job is to add what they don't: it discloses upstream rate limiting and the hard refusal of outward-only codes. That is exactly the kind of operational context annotations can't express; only error/return shape is left unstated (and an output schema exists).
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?
Two short sentences, resource first then constraint, zero filler. Every clause carries information the agent can act on.
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 a single required param, full schema coverage, and an output schema, the description covers the essentials plus rate-limit and input-validity caveats. It stops short of only minor items such as response size or what happens on a valid-but-unmatched postcode.
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 an example already present, so baseline is 3. The description goes beyond the schema by stating which form of postcode is rejected (outward-only, e.g. NW2), which prevents a plausible failed call the schema alone would permit.
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 specifically that the tool returns addresses for a full UK postcode, with a concrete example. It doesn't need to distinguish from siblings since none of the listed tools overlap, but it also never names or rules out an alternative.
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 exclusion 'a partial postcode ... is refused' gives the agent one clear precondition, which is genuinely useful. There is no broader when-to-use framing or pointer to another tool for partial/outward-code lookups, so guidance is implied rather than complete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.