Asian Recs

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds real value by enumerating the returned payload (both ratings and the gap, Asian reviewer share, mentioned dishes, quotes, Google/Yelp ratings, links), which is important since there is no output schema. It does not, however, disclose behavior for ambiguous or missing place names, which matters given the optional 'type' disambiguator.

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?

Purpose is front-loaded in the first clause, and the second sentence gives the usage trigger. The long enumeration of return fields is justified by the absence of an output schema, though it reads as a list dump rather than tightly integrated prose.

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 no output schema and no annotations covering return values, the description correctly compensates by spelling out the payload. Usage context and geographic limits are present. The main remaining gap is failure/ambiguity behavior, which the description leaves to the optional 'type' parameter in the schema.

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% and every parameter is documented inline, including the city enum labels and the note that partial names work, so the description's 'San Francisco or New York' phrasing merely echoes the enum. Baseline 3 is appropriate when the schema carries the parameter meaning.

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 and resource ('Full Asian Recs page for one place') and enumerates exactly what that page contains, so an agent knows it retrieves a single rich record. It implicitly distinguishes itself from search_places via the singular 'one place,' but never names the sibling, so the differentiation is inferential rather than explicit.

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?

'Use when someone asks about one specific place in San Francisco or New York' gives a clear triggering condition and a geographic scope constraint. It stops short of naming search_places as the alternative when the user asks about a category or multiple places, so the routing is implied rather than stated.

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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so safety is covered. The description adds one useful piece of context beyond the name — that each entry includes a count of ranked places, which hints at the return shape. It says nothing about cache freshness, ordering, or whether results change over time.

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 tightly written sentences with zero filler. The core purpose is front-loaded, followed immediately by the usage framing.

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 no output schema, the description must gesture at return content, and it does by mentioning the places-per-entry count. For a simple two-enum read-only lookup this is nearly sufficient, though a bit more on the returned grouping (areas vs neighborhoods vs cuisines) would fully close the gap.

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% and both parameters carry enum value definitions with clarifying notes (e.g. boba/coffee/tea map to cafes). The description only restates 'city and kind of place' generically, adding no enum or default semantics beyond the schema — baseline 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?

States a specific verb and resource — lists the areas, neighborhoods and cuisines available for a given city and place type — and adds the distinguishing detail that each carries a count of ranked places. It explicitly positions itself relative to the search_places sibling by noting it resolves the exact names that tool accepts.

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 two concrete use cases: resolving exact neighborhood/cuisine names for search_places, or answering coverage questions. The alternative (search_places) is named, but there is no explicit when-not guidance or mention of the get_place sibling, so it falls short of a full 5.

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real value by enumerating the returned fields (both ratings, the gap, review counts, top dishes, neighborhood, link) and by disclosing empty-result behavior ('message says why').

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 tight sentences, none of them filler: capability and ranking first, usage triggers second, empty-state behavior last. Nothing is repeated and nothing is buried.

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 no output schema, the description correctly compensates by listing the result fields, and the nine params are fully covered by the schema. Only minor gaps remain, such as pagination or how limit interacts with ranking, which are not addressed anywhere.

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% and every parameter, including the enums and the near/radius interaction, is documented in the schema itself. The description adds no syntax, format, or default information beyond what the schema provides, so the baseline 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?

States a specific verb (find), resource (places), geography (San Francisco or New York), and the distinctive ranking signal (how Asian diners rate them). It does not, however, differentiate itself from siblings get_place or list_filters, leaving the agent to infer that get_place is for detail lookups.

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 clear triggering contexts: 'when someone asks where to eat or drink' and 'restaurant, dessert, cafe or bar recommendations' in the two supported cities. No explicit when-not-to-use or named alternatives, which keeps it short of a 5.

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