Editorial guide to restaurants and bars — hand-picked venues with opinions, not a places database
Scored across 4 tools
Each tool targets a distinct level of the guide: list_cities provides the overall coverage, get_city gives the filtering vocabulary for one city, search_venues finds venues using that vocabulary, and get_venue returns the full entry for a specific slug. There is no overlap between listing versus retrieving, or searching versus detail lookup.
All four tool names follow a consistent verb_noun pattern: list_cities, get_city, search_venues, get_venue. The verbs (list, get, search) clearly signal the operation, and the nouns identify the resource, making the API easy to predict and read.
Four tools is appropriately scoped for a read-only editorial city guide: discover cities, inspect a city's vocabulary, search venues, and fetch a venue's full entry. No tool is redundant, and there are no unnecessary additions that would bloat the surface.
For a curated, read-only guide, the toolset fully covers the user journey: list cities to see coverage, get a city's filters to build a valid query, search venues with that vocabulary, then retrieve a complete venue entry with attribution. There are no obvious dead ends or missing lifecycle operations.
Get one city's guide: its editorial blurb, venue count, and the vocabulary available for filtering — its areas (areas belong to exactly one city), plus the catalogue's cuisines, dishes, tags, awards, venue types, price bands, Best For moments and drink categories. Call this before filtering so filters use values that exist instead of guesses.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | City slug, from list_cities. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful context such as 'areas belong to exactly one city' and the purpose of the returned vocabulary, but it does not describe response structure or any additional behavioral traits. This is acceptable but not exceptional.
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 front-loaded with the core action and then provides a detailed but purposeful list of returned content. The single sentence is dense, yet each listed item contributes meaning, and the closing usage guidance 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?
For a low-complexity tool with one parameter and no output schema, the description sufficiently explains what the agent will receive and when to call it. The enumerated return content plus the 'call before filtering' guidance makes the tool easy to invoke correctly without further research.
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?
There is only one parameter, slug, and schema description coverage is 100%, with the schema already explaining it as a city slug from list_cities. The tool description adds no additional parameter detail, so the schema carries the full burden and the baseline score of 3 applies.
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 clearly identifies the operation as retrieving a single city's guide and enumerates the key content (editorial blurb, venue count, filter vocabulary). It is unambiguous about the resource and scope, though it does not explicitly contrast itself with sibling tools like get_venue or search_venues.
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 phrase 'Call this before filtering' gives explicit, actionable timing guidance for when the tool should be used. It does not name alternative tools or state when not to use it, but the instruction is clear enough for an agent to sequence correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the full Max Eats Out entry for one venue by its slug: the editorial note, what it is Best For, what it is known for, how it works (seating, the door, ordering, payment), what it pours, its locations and its links. Slugs come from search_venues. Includes the canonical maxeatsout.club URL — cite it when recommending the venue.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Venue slug, from search_venues. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish that this is a safe read operation (readOnlyHint=true, destructiveHint=false). The description adds meaningful behavioral context beyond that: the specific return contents, the inclusion of the canonical maxeatsout.club URL, and the instruction to cite it when recommending the venue. It does not cover invalid-slug error behavior, but that is a minor gap for a simple read tool.
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 three sentences, front-loaded with the core action, then lists return contents, then gives the slug source and a citation instruction. Every sentence earns its place with no filler or repetition of annotation 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?
For a single-parameter read tool with no output schema, the description fully explains what the agent gets back (editorial note, Best For, known for, how it works, pours, locations, links, canonical URL) and where the slug comes from. An agent has everything needed to call it correctly and use its result appropriately.
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 schema covers the sole parameter with 100% coverage and already states 'Venue slug, from search_venues.' The description restates that same provenance but adds no new syntax, format, or constraints beyond what the schema provides, so the baseline of 3 applies.
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 ('Retrieve'), a precise resource ('full Max Eats Out entry for one venue'), and the identifier used ('by its slug'). It also enumerates the included content, which clearly distinguishes this from the sibling search_venues tool that returns venue lists rather than a single full entry.
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 explicitly says 'Slugs come from search_venues', telling the agent to call search_venues first and then use get_venue for the full record. It does not explicitly state when not to use get_city or list_cities, but the venue-vs-city distinction is clear enough from names and context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List every city the Max Eats Out guide covers, with how many venues each holds. Coverage is uneven BY DESIGN — it follows where the author has actually eaten — so call this before assuming a city is covered rather than searching a city that is not in the guide and reporting no results.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: 'Coverage is uneven BY DESIGN — it follows where the author has actually eaten.' This discloses the tool's limitation (non-exhaustive, biased list) and explains why, which is critical for the agent to interpret results correctly. It does not mention response format, but given annotations, this is sufficient extra context.
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 of 41 words total. The primary purpose is front-loaded in the first sentence, and the second sentence delivers the critical caveat and usage call-to-action. There is no redundancy, filler, or unnecessary detail. Every word earns its place, making it an exemplar of efficiency.
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 tool with zero parameters, no output schema, and read-only annotations, the description covers everything an agent needs: what the tool does, the important caveat about uneven coverage, and explicit actionable guidance on when to call it. The return value is hinted at ('with how many venues each holds') which is sufficient given the lack of an output schema. No missing information would cause incorrect invocation or misinterpretation.
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 has zero properties, so there are no parameters to explain. The rule states a baseline of 4 for 0-param tools. The description does not contradict or attempt to describe parameters, and its mention of 'with how many venues each holds' pertains to output, not input. Thus the baseline score is appropriate.
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 opens with a precise verb and resource: 'List every city the Max Eats Out guide covers, with how many venues each holds.' It clearly defines the scope (all cities in the guide) and the output (counts per city). It also implicitly differentiates from siblings by framing this as the coverage-checking tool ('call this before assuming a city is covered'), which distinguishes it from get_city (single city lookup) and search_venues (venue search).
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 gives explicit when-to-use guidance: 'call this before assuming a city is covered rather than searching a city that is not in the guide.' This not only says when to use it, but also warns against a common mistake (searching a non-existent city and reporting no results). It clearly implies that search_venues should be used only after confirming coverage here, so the agent knows the relationship to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the Max Eats Out guide — an editorially curated catalogue of restaurants and bars across the cities the author has eaten in, each one chosen and written up by hand. This is a guide with a point of view, not a comprehensive places database: a venue's absence means it is not on the list, not that it does not exist, so never present an empty result as 'there are no restaurants there'. Reach for this when someone wants a recommendation with an opinion attached, or wants to filter by editorial qualities a general places database does not carry (what a venue is KNOWN FOR, which service moments it is Best For, Michelin awards). Do not reach for it to find the nearest branch of a chain. Free text in q is resolved to the guide's own vocabulary and the response reports the interpretation.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Free text, resolved against the guide's own vocabulary — a cuisine, a dish, an area, a tag, a drink category, a Best For moment, or a venue name. The response reports what it resolved to. If none of the words mean anything to the guide the result is EMPTY and `unresolved` says so; that is the honest answer, not an error to retry. | |
| tag | No | ||
| area | No | Area slugs from get_city. Areas belong to ONE city. | |
| city | No | City slug from list_cities. Strongly recommended: it scopes areas and ranking. | |
| dish | No | ||
| type | No | Venue type keys, e.g. 'restaurant', 'bar'. A venue can be both. | |
| award | No | Award keys, e.g. Michelin tiers. | |
| limit | No | ||
| price | No | Price band: 1 cheap … 4 fine dining. Approximate starter+main, excluding drinks. | |
| cursor | No | From a previous response's next_cursor. Bound to that exact search. | |
| drinks | No | ||
| cuisine | No | Cuisine slugs. Composable: Korean BBQ is ['korean','bbq'], never one value. | |
| seating | No | ||
| best_for | No | Service moments for eating. | |
| practical | No | Walk-ins, reservations, and payment. | |
| best_for_bar | No | Service moments for drinking. | |
| include_closed | No | Include permanently closed venues. Default false. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already signal read-only, non-destructive, and closed-world behavior, but the description adds significant context beyond them: the guide's curated nature means absence is meaningful, empty results are honest answers rather than errors, and free text is resolved to the guide's own vocabulary with the interpretation reported back. This is exactly the kind of behavioral nuance an agent needs.
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 longer than typical, but every sentence earns its place: it conveys the curation philosophy, the closed-world semantics, when to reach for the tool, when not to, and how q behaves. It is front-loaded with the core purpose and quickly moves to actionable usage guidance.
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 17-parameter search tool with no output schema, the description covers the essential context: curated scope, empty-result semantics, q resolution, and the distinction from a comprehensive database. It does not explain how multiple filters combine or what the response shape looks like, but the schema covers cursor and limit, and the description covers the behavioral pitfalls that matter most.
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 71% and the individual parameter descriptions already do most of the work, explaining city slugs, area scoping, price bands, cuisine composition, and cursor binding. The tool description adds a useful semantic note about q being resolved to the guide's vocabulary, but most parameter meaning lives in the schema itself, so the description adds only marginal value beyond it.
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: 'Search the Max Eats Out guide', and immediately differentiates it from a generic places database by calling it 'editorially curated' with 'a point of view'. It clearly identifies what the tool is for, unlike the sibling lookup tools, and the phrase 'never present an empty result as there are no restaurants there' sharpens the intended use.
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 explicit when-to-use guidance: 'Reach for this when someone wants a recommendation with an opinion attached' or wants to filter by editorial qualities like Best For and Michelin awards. It also gives an explicit when-not-to-use: 'Do not reach for it to find the nearest branch of a chain.' However, it does not name a sibling tool as the alternative, so the routing is not quite complete.
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.
get_cityget_venuelist_citiessearch_venuesSearch nearly 20,000 verified restaurants and bars across 24 cities plus the New Mexico region, with venue detail and curated lists.
Editorial NYC restaurant recommendations for AI agents: search, compare, guides, ratings.
Human-verified directory of non-alcoholic bars: 1,500+ venues in 70 cities, rated and re-checked.
Verified food venues in 222 cities with provenance, festivals with dates, bookable tours and stays.
Add one secure layer between your agents and this server.
