NYC Restaurant Week

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

No annotations are provided, so the description carries the full burden. It discloses the behavioral logic: returns program week, Saturday exclusion, Sunday limitations, and participation count. It does not explicitly state side-effect-free or error behavior, but the 'check' nature makes it clear it is a read-only operation.

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 efficiently states the action, input format, and output details without any fluff. Every part is informative and necessary.

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 simple one-parameter tool with no annotations or output schema, the description adequately explains the check logic and return content (rules, program week, exclusions, participation count). It could mention edge cases like invalid dates, but the schema pattern already restricts input, making it sufficiently complete.

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 only parameter 'date' with a description ('Date to check, YYYY-MM-DD') and pattern. The description restates the format and adds context about its role in evaluating Restaurant Week, but this adds minimal value beyond the schema's existing description. Baseline of 3 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 clearly states the tool's purpose: checking whether a date falls within NYC Restaurant Week Summer 2026 and returning day-specific rules and participation count. This is a specific verb+resource combination that is distinct from sibling tools like get_restaurant, list_filters, and search_restaurants.

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 when to use the tool: when you have a date and need to know if it falls within Restaurant Week and what rules apply. It provides clear context but does not explicitly mention alternatives or exclusions, though siblings are obviously different in scope.

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?

With no annotations, the description carries the burden of behavioral disclosure. It conveys a safe read-only operation by using 'Get' and explicitly lists the output fields, so an agent can predict what will happen. It does not mention error behavior or permissions, but for a simple read-only lookup this is a minor gap.

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 specific return contents. Every phrase adds value, with no filler or redundancy.

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 one-parameter read-only lookup with no output schema, the description is nearly complete: it identifies the exact output fields, input format, and the singular scope. It could mention what happens when a restaurant is not found or not participating, but this is a minor omission for such a simple tool.

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 provides 100% parameter documentation, including the accepted forms (slug from search_restaurants or name) and an example. The description reinforces 'by slug or name' but does not add substantive meaning beyond the schema, 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 uses a specific verb and resource ('Get full details for one participating restaurant') and enumerates the returned data (description, prix-fixe offers, weeks, PDF, website, OpenTable link), making its function unmistakable. It also clearly differentiates from the sibling search_restaurants tool by targeting a single restaurant rather than a search/listing.

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 clearly implies when to use the tool: when you need full details for a specific restaurant, with the input being a slug or name. It does not explicitly discuss alternatives or exclusions, but the singular 'one restaurant' and the schema hint that the slug comes from search_restaurants provide clear context.

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?

With no annotations, the description carries the full burden. It discloses the content (filter values with counts, including program weeks with dates) but does not discuss output format, ordering, or performance characteristics. It adds some value beyond the name but could be more explicit about response structure.

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 sentences, front-loaded with the action, each sentence earning its place: the first describes the content, the second gives usage context. No wasted words.

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 zero-parameter listing tool with no output schema, the description is appropriately complete: it explains what is returned and when to use it. The only gap is lack of detail on how the output is structured, but this is minor given the tool's simplicity.

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 tool has zero parameters, so the schema provides full coverage. The description does not need to explain parameters; the baseline for 0-parameter tools is 4.

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 states the tool lists every available filter value with participant counts, enumerating specific categories (cuisines, boroughs, neighborhoods, price tiers, meals, curated collections, program weeks). It uses a specific verb ('List') and resource, distinguishing it from siblings like search_restaurants or get_restaurant.

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?

Provides clear usage context with 'Useful before searching, or to summarize the program,' indicating when to invoke it. It does not explicitly name alternatives or exclusions, but the context makes it distinct from sibling tools.

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?

With no annotations, the description carries the transparency burden. It discloses the exact scope (636 restaurants, date range), price tiers, Saturday exclusion, and Sunday variability, which are behavioral quirks not obvious from the schema. Also mentions pagination and the presence of slugs for follow-up. Strong coverage, though it could be more explicit about the exact result item structure.

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 sentences, front-loaded with the core action and scope. Each sentence contributes: scope, filter flexibility/pricing/date quirks, and output/pagination/follow-up. Zero extraneous words.

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 14 optional parameters and no output schema, the description provides essential program context (dates, tiers, exclusions), explains that the result is a paginated list with total count, and points to get_restaurant for further detail by slug. This covers the main decision points, though a bit more detail about ordering or result fields would make it completely self-contained.

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 high (86%), so baseline is 3. The description adds value by explaining that filters are combinable and by cluing the date/sunday parameters to program rules (Saturdays excluded, Sundays vary). It also clarifies the meaning of price tiers in context, raising it above the baseline.

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?

Opens with a specific verb 'Search' and identifies the exact dataset: 636 restaurants in NYC Restaurant Week Summer 2026 with a date range. Distinguishes from get_restaurant by noting that detailed menus and reservations come from that tool. Clear, specific, and differentiates from siblings.

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?

States all filters are optional and combinable, and provides program-level constraints (Saturdays excluded, Sundays vary) that affect when to use certain filters. Explicitly directs users to get_restaurant for more details after finding a restaurant, and mentions pagination. Gives clear when-to-use context and sibling guidance.

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