Find the practice served by this connection by borough and publicly listed service. This is an office directory lookup, not a search of all dentists. A location mismatch returns no results.
| Name | Required | Description | Default |
|---|---|---|---|
| service | No | ||
| location | No |
| Name | Required | Description | Default |
|---|---|---|---|
| practices | Yes | ||
| source_status | Yes | ||
| sources_checked | Yes | ||
| information_may_be_outdated | Yes |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": false,
+ "properties": {
+ "information_may_be_outdated": {
+ "type": "boolean"
+ },
+ "practices": {
+ "items": {
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "source_status": {
+ "type": "string"
+ },
+ "sources_checked": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "sources_checked",
+ "information_may_be_outdated",
+ "source_status",
+ "practices"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, closedWorld and non-destructive, so the safety profile is covered. The description adds one useful behavior beyond that — a mismatched location yields an empty result rather than an error or fallback — but says nothing about how omitted/optional parameters behave.
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?
Three short sentences, front-loaded with the core action and followed immediately by the two most likely misreadings. 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?
An output schema exists, so return values need no explanation, and annotations carry the safety profile. Scope, input dimensions, and the failure mode are all present; the only minor gap, defaults for the optional enums, is small enough that an agent can still call this correctly.
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 0%, so the description must compensate, and it only partly does: 'borough' and 'publicly listed service' map intuitively onto the location and service enums. It does not explain that both parameters are optional, nor what the 'any' enum value does when omitted.
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 (find the practice) scoped by borough and publicly listed service, and explicitly negates the broader interpretation ('not a search of all dentists'). It does not differentiate against nearby siblings like get_practice_details or get_office_hours, which an agent could easily confuse with this lookup.
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 the agent a clear condition for when not to use it (not a general dentist search) and a constraint that shapes input choice ('A location mismatch returns no results'). No sibling alternative is named, so routing is implied rather than directed.
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.