Read-only travel tipping for 140 destinations: search, country rules, and tip calculator.
Scored across 3 tools
Each tool has a clearly distinct purpose: calculate_tip computes amounts, get_tipping_rules retrieves guidance for a specific destination, and search_countries finds destinations. There is no functional overlap between them, so an agent can unambiguously select the right tool for each task.
All tool names follow a consistent verb_noun pattern: calculate_tip, get_tipping_rules, search_countries. The verbs are specific and the nouns correspond to the resource they act on, creating a predictable and readable naming scheme.
With 3 tools, the server is tightly scoped to the domain of tipping rules. Each tool covers a distinct core operation—searching, retrieving details, and calculating tips—so none feel redundant or missing, making the count ideal for its narrow purpose.
The tool surface fully covers the expected workflow: discover destinations via search_countries, access detailed guidance via get_tipping_rules, and apply that guidance via calculate_tip. There are no obvious dead ends or missing operations for the stated domain, making the set complete.
Calculate a suggested tip and total for a bill using Tipping Rules destination norms (percent or round-up). Returns amounts plus canonical destination and calculator URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| bill | Yes | Bill amount in local currency units (positive number). | |
| country | Yes | Country slug or name for local tipping norms. | |
| service | No | Service category. Prefer restaurant, bar, taxi, delivery, hotelStaff, or tourGuides. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context beyond the annotations by disclosing the calculation mode ('percent or round-up'), that it uses destination norms, and that it returns URLs alongside amounts. Since readOnlyHint, idempotentHint, and destructiveHint already cover the safety profile, the description contributes useful non-obvious behavior.
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 description is two sentences with no filler, front-loading the core purpose ('Calculate a suggested tip and total') before adding method and output details. Every clause contributes non-redundant information.
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 the annotations, complete input schema, and presence of an output schema, the description is largely sufficient for an agent to invoke the tool correctly. Minor gaps include the lack of explicit guidance on sibling tool selection and no clarification of default behavior when the optional service parameter is omitted.
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%, so the baseline is 3. The description does not add parameter-level details beyond the schema: bill, country, and service are already semantically described in the input schema's property descriptions. The mention of destination norms slightly reinforces country semantics but does not substantially extend them.
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 action verb ('Calculate') and identifies the resource ('a suggested tip and total for a bill'), plus the method ('Tipping Rules destination norms') and outputs ('amounts plus canonical destination and calculator URLs'). This distinguishes it clearly from siblings get_tipping_rules and search_countries.
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 description implies usage for computing tip amounts and totals, but it does not explicitly state when to choose this tool over get_tipping_rules or search_countries. There are no exclusion conditions or alternative routing hints, so the agent must infer the appropriate context from the tool name and sibling list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get concise tipping guidance for a destination: status, summary, key service recommendations, last reviewed date, and the canonical page URL.
| Name | Required | Description | Default |
|---|---|---|---|
| country | Yes | Country slug (preferred) or country name, e.g. japan or Japan. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds value by specifying the output content (status, summary, recommendations, last reviewed date, URL), which goes beyond the annotations. No contradictions; the additional detail about the response is useful.
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 description is a single, well-structured sentence that front-loads the primary action and then lists the key output components. No redundancy or extraneous detail; every element earns its place.
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?
The tool is simple (one parameter) and has an output schema that presumably documents the return structure. The description lists the main fields returned, which covers what an agent needs to know. No missing information for correct invocation.
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?
The input schema already describes the single parameter (country) with clear guidance on slug vs name. Schema description coverage is 100%, so the schema carries the semantic burden. The description does not add parameter-specific information beyond mentioning 'destination' in the output context, so baseline 3 is correct.
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 ('Get') and resource ('tipping guidance for a destination') and enumerates the content returned (status, summary, recommendations, last reviewed date, URL). This clearly distinguishes it from sibling tools like calculate_tip (which would calculate a tip amount) and search_countries (which searches destinations).
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 description implies usage for obtaining guidance rather than performing calculations, which differentiates it from calculate_tip. However, it does not explicitly state when to use this tool versus alternatives or provide exclusions. Given the clear context, a 4 is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Tipping Rules destinations by name or region. Returns matching destinations with status and canonical page URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Country name, alias, or region fragment to search. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and non-destructive behavior, so the description doesn't need to repeat that. It adds useful behavioral detail beyond annotations by specifying that results include status and canonical page URLs. Pagination/limits are not mentioned, but the output schema likely covers the remaining shape.
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 tight sentences with the purpose front-loaded and no filler. Each clause adds operational value: scope ('by name or region') and return shape ('status and canonical page URLs').
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 single-parameter, read-only search with rich annotations and an output schema, this description is complete. It covers scope and return behavior, while the schema covers constraints such as min/max length and requiredness.
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%: the query parameter is already described as 'Country name, alias, or region fragment to search.' The description mirrors name or region but adds no parameter details beyond the schema. Baseline 3 is appropriate when the schema carries the parameter semantics.
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?
Description names a specific verb ('Search'), a specific resource ('Tipping Rules destinations'), search criteria (name or region), and return contents (status and canonical page URLs). This clearly distinguishes it from sibling tools calculate_tip and get_tipping_rules.
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 description establishes clear context: this is the destination discovery/read tool for Tipping Rules. It does not explicitly state when not to use it, but the siblings are obviously different operations, so an agent can infer the right selection without extra guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
calculate_tip1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "anyOf": [
+ {
+ "additionalProperties": false,
+ "properties": {
+ "bill": {
+ "description": "Bill amount in local currency units.",
+ "exclusiveMinimum": 0,
+ "type": "number"
+ },
+ "calculatorUrl": {
+ "description": "Deep link to the on-site calculator for this country.",
+ "format": "uri",
+ "type": "string"
+ },
+ "canonicalUrl": {
+ "description": "Canonical country page URL.",
+ "format": "uri",
+ "type": "string"
+ },
+ "country": {
+ "description": "Display name of the destination.",
+ "type": "string"
+ },
+ "currency": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "ISO currency code when known (e.g. EUR, USD)."
+ },
+ "lastReviewed": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "ISO date when guidance was last reviewed, when available."
+ },
+ "methodologyUrl": {
+ "description": "How Tipping Rules reviews and sources guidance.",
+ "format": "uri",
+ "type": "string"
+ },
+ "mode": {
+ "description": "Calculation mode applied for this service and destination.",
+ "enum": [
+ "percent",
+ "round_up",
+ "zero"
+ ],
+ "type": "string"
+ },
+ "ok": {
+ "const": true,
+ "description": "True when the tip was calculated.",
+ "type": "boolean"
+ },
+ "recommendation": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Human-readable norm string for the selected service."
+ },
+ "service": {
+ "description": "Service category label used for the calculation.",
+ "type": "string"
+ },
+ "slug": {
+ "description": "Country slug.",
+ "type": "string"
+ },
+ "source": {
+ "const": "Tipping Rules",
+ "description": "Attribution for downstream citations.",
+ "type": "string"
+ },
+ "tipAmount": {
+ "description": "Suggested tip amount in local currency units.",
+ "type": "number"
+ },
+ "tipPercent": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Applied tip percent when mode is percent; null for round-up."
+ },
+ "total": {
+ "description": "Bill plus suggested tip.",
+ "type": "number"
+ }
+ },
+ "required": [
+ "ok",
+ "country",
+ "slug",
+ "service",
+ "bill",
+ "currency",
+ "mode",
+ "tipPercent",
+ "tipAmount",
+ "total",
+ "recommendation",
+ "lastReviewed",
+ "canonicalUrl",
+ "calculatorUrl",
+ "methodologyUrl",
+ "source"
+ ],
+ "type": "object"
+ },
+ {
+ "additionalProperties": false,
+ "properties": {
+ "code": {
+ "description": "Machine-readable error code (e.g. NOT_FOUND, VALIDATION, TIMEOUT).",
+ "type": "string"
+ },
+ "message": {
+ "description": "Short, agent-safe error message.",
+ "type": "string"
+ },
+ "ok": {
+ "const": false,
+ "description": "False when the tool could not complete successfully.",
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "ok",
+ "code",
+ "message"
+ ],
+ "type": "object"
+ }
+ ],
+ "description": "Tip calculation result or a structured error.",
+ "type": "object"
+}get_tipping_rules1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "anyOf": [
+ {
+ "additionalProperties": false,
+ "properties": {
+ "canonicalUrl": {
+ "description": "Canonical country page URL.",
+ "format": "uri",
+ "type": "string"
+ },
+ "country": {
+ "description": "Display name of the destination.",
+ "type": "string"
+ },
+ "lastReviewed": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "ISO date when guidance was last reviewed, when available."
+ },
+ "methodologyUrl": {
+ "description": "How Tipping Rules reviews and sources guidance.",
+ "format": "uri",
+ "type": "string"
+ },
+ "ok": {
+ "const": true,
+ "description": "True when country guidance was loaded.",
+ "type": "boolean"
+ },
+ "situations": {
+ "description": "Key service recommendations (up to 8).",
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "expectation": {
+ "description": "Overall tipping expectation context for the destination.",
+ "type": "string"
+ },
+ "recommendation": {
+ "description": "Concise tipping recommendation for the service.",
+ "type": "string"
+ },
+ "service": {
+ "description": "Service category label (e.g. Restaurant, Taxi).",
+ "type": "string"
+ }
+ },
+ "required": [
+ "service",
+ "recommendation",
+ "expectation"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "slug": {
+ "description": "Country slug.",
+ "type": "string"
+ },
+ "source": {
+ "const": "Tipping Rules",
+ "description": "Attribution for downstream citations.",
+ "type": "string"
+ },
+ "status": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Overall tipping expectation label, when available."
+ },
+ "summary": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Short editorial summary of local tipping norms."
+ }
+ },
+ "required": [
+ "ok",
+ "country",
+ "slug",
+ "status",
+ "summary",
+ "situations",
+ "lastReviewed",
+ "canonicalUrl",
+ "methodologyUrl",
+ "source"
+ ],
+ "type": "object"
+ },
+ {
+ "additionalProperties": false,
+ "properties": {
+ "code": {
+ "description": "Machine-readable error code (e.g. NOT_FOUND, VALIDATION, TIMEOUT).",
+ "type": "string"
+ },
+ "message": {
+ "description": "Short, agent-safe error message.",
+ "type": "string"
+ },
+ "ok": {
+ "const": false,
+ "description": "False when the tool could not complete successfully.",
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "ok",
+ "code",
+ "message"
+ ],
+ "type": "object"
+ }
+ ],
+ "description": "Country tipping guidance or a structured error.",
+ "type": "object"
+}search_countries1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "anyOf": [
+ {
+ "additionalProperties": false,
+ "properties": {
+ "count": {
+ "description": "Number of destinations returned (max 8).",
+ "maximum": 9007199254740991,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "methodologyUrl": {
+ "description": "How Tipping Rules reviews and sources guidance.",
+ "format": "uri",
+ "type": "string"
+ },
+ "ok": {
+ "const": true,
+ "description": "True when search completed successfully.",
+ "type": "boolean"
+ },
+ "query": {
+ "description": "Echo of the submitted search query.",
+ "type": "string"
+ },
+ "results": {
+ "description": "Matching destinations ordered by relevance.",
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "canonicalUrl": {
+ "description": "Canonical country page URL on tippingrules.com.",
+ "format": "uri",
+ "type": "string"
+ },
+ "name": {
+ "description": "Display name of the destination.",
+ "type": "string"
+ },
+ "region": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Region label from the catalog, when available."
+ },
+ "slug": {
+ "description": "Country slug for follow-up tool calls.",
+ "type": "string"
+ },
+ "status": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Tipping expectation label, when available."
+ }
+ },
+ "required": [
+ "slug",
+ "name",
+ "status",
+ "region",
+ "canonicalUrl"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "source": {
+ "const": "Tipping Rules",
+ "description": "Attribution for downstream citations.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "ok",
+ "query",
+ "count",
+ "results",
+ "methodologyUrl",
+ "source"
+ ],
+ "type": "object"
+ },
+ {
+ "additionalProperties": false,
+ "properties": {
+ "code": {
+ "description": "Machine-readable error code (e.g. NOT_FOUND, VALIDATION, TIMEOUT).",
+ "type": "string"
+ },
+ "message": {
+ "description": "Short, agent-safe error message.",
+ "type": "string"
+ },
+ "ok": {
+ "const": false,
+ "description": "False when the tool could not complete successfully.",
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "ok",
+ "code",
+ "message"
+ ],
+ "type": "object"
+ }
+ ],
+ "description": "Search results or a structured error.",
+ "type": "object"
+}calculate_tipget_tipping_rulessearch_countriesRead-only payroll calculations and multi-country tax comparisons for eight countries.
Read-only public transit departures, stop search, and city coverage for bus and train users.
Search and explore a global travel points-of-interest catalog (cities, countries, POIs).
Read-only U.S. lab-test catalog, collection-site search, and reference-range context.
Add one secure layer between your agents and this server.
