兔兔生活（爱佳肴 Love Life）

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 usefully discloses that the wake word (兔兔生活/tutulife) is auto-detected and should be left in the input, but says nothing about whether this is a read-only query, what form the answer takes, latency, or whether the optional location params are honored.

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 short sentences, bilingual by design, with the key instruction (use first, pass verbatim) front-loaded. Slightly redundant across the Chinese/English versions but efficient overall.

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 annotations and no output schema, the description should explain what the agent gets back (a spoken answer? a suggestion list?) and when location params are needed. It covers routing and input handling but leaves the return behavior and optional-parameter semantics unaddressed, which is a meaningful gap for a 5-param NL 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?

Schema description coverage is 80% (lat, lng, near, question all documented), so the schema already does most of the work. The description adds one genuinely non-obvious point for the required 'question' param — pass verbatim and keep the wake word in — but says nothing about lat/lng/city/near or how they interact with the question text.

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 capability: answering natural-language 'what/where to eat' questions by passing the user's words verbatim, with wake-word auto-detection. It is clearly distinguishable from CRUD siblings like get_restaurant, though it never names search_restaurants, the closest alternative, so sibling differentiation is only implied via 'use first'.

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?

It gives explicit precedence guidance ('首选' / 'Use first for any where to eat question'), which tells the agent to route here before other tools. It stops short of stating when NOT to use it or naming the fallback sibling (e.g. search_restaurants, tell_us_your_need).

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?

No annotations are provided, so the description carries the full behavioral burden. It discloses that feedback is returned raw and per-item (the one genuinely useful trait), but says nothing about pagination behavior, auth/permission needs, or the shape of a feedback record.

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 content is short and the usage condition is front-loaded, but the Chinese and English sentences are literal duplicates, so the second sentence adds no information and the listing is padded rather than dense.

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 paginated list tool with no annotations and no output schema, the description leaves too much unsaid: it doesn't describe what a raw feedback item contains, how paging works, or when results are empty. The agent is given a use case but not enough to call it 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% and all three parameters (store_id, limit, offset) are undocumented in the schema. The description implies a per-store scope but never explains store_id format or how limit/offset control the result set, so it fails to compensate for the coverage gap.

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 (return) and resource (raw per-item feedback for one store), and the phrase '逐条原始反馈' distinguishes it from any aggregated/summarized feedback a sibling might provide. However, it never names a sibling such as get_restaurant explicitly, so differentiation is implied rather than stated.

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?

'想自行判断...口碑可信度时用' gives a clear when-to-use condition (when the agent wants to judge credibility itself from raw data). But it names no alternative tool and no exclusion, so the agent must infer how this differs from get_restaurant or search_restaurants.

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 behavioral burden. It implies a read-only lookup (核对/verify) and discloses the returned data categories, which is useful, but it says nothing about permissions, error behavior when a store id is invalid, or rate limits. Adequate but incomplete for a zero-annotation 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 definition is short and front-loaded, but it is the same content stated twice (Chinese then English) with no added information in the second sentence. Roughly half the text is redundant, so it does not fully earn its length even though nothing is verbose.

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?

Complexity is low (one required id, no nested objects) and no output schema exists, so the description must convey return content — which it does by listing hours, price, menu, and freshness. Combined with the pre-recommendation usage note, this is nearly complete for the tool's complexity.

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 a single parameter (store_id) at 100% schema description coverage, so the schema already documents it ('店铺 id / store id'). The description adds no format, sourcing, or lookup semantics beyond what the schema provides, which is the expected baseline at this coverage.

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 clear verb+resource (fetch/verify one store) and enumerates the returned content (hours, average price, menu, freshness), so an agent knows what it gets. It does not, however, differentiate itself from siblings like search_restaurants or ask_restaurants, leaving the distinctive 'single store by id' role implicit.

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?

'Before recommending it' supplies an implied usage condition — call this when you have a store id and need to validate it prior to a recommendation. There is no explicit statement of when not to use it, nor a named alternative (e.g. search_restaurants) for discovering stores, so the routing guidance is only partial.

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?

No annotations are provided, so the description carries the full burden, and it does usable work: it discloses row ordering (misses descending), a minimum threshold (fewer than 2 misses omitted), a hard cap (max 100), and a privacy constraint (aggregated counts only, no raw user queries). It does not say whether results are cached or how fresh the aggregation is, which keeps it below 5.

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 content is front-loaded and information-dense, but every sentence is duplicated in Chinese and English, roughly doubling the length without adding information. Useful facts (sort order, threshold, cap) do each earn their place, but the redundancy costs structure points.

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 compensates by enumerating the returned item fields, their nullability, the ISO 8601 UTC format, ordering, filtering thresholds and the 100-row cap. That is close to complete for a read-only aggregate tool; only freshness/latency and date-window interaction remain unspecified.

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%, with both city and days fully documented including defaults and ranges, so the baseline is 3. The description restates the output fields rather than adding parameter behavior (e.g. interaction between city and days, or what happens at window edges), adding little beyond the schema.

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 resource and what it represents: aggregated unmet-demand gaps (需求缺口) with city/district/want/asks/misses. It identifies its consumers (site-picking and data-gap agents) but never names a sibling tool, so differentiation from ask_restaurants, tell_us_your_need or search_restaurants is left implicit 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?

Gives concrete usage triggers: use after an empty search, or when you want to see where stores are missing. That is a clear context for invocation. There is no explicit when-not to call it, so it stops short of the top score.

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?

No annotations are provided, so the description carries the full behavioral burden, and it does almost none of that work. It does not state that this is a read-only, non-mutating search, does not explain pagination behavior via limit/offset, and says nothing about result volume or ordering.

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 short sentences, front-loaded with the filtering condition before the English restatement. The bilingual duplication conveys no new information but is defensible for a mixed-language audience, so the cost is minor.

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 13-parameter tool with no annotations, no output schema, and 54% schema coverage, the description is far too thin. It omits pagination semantics, keyword-search behavior, coordinate-system implications for the geo params, and any indication of what a result contains.

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?

With 13 parameters and only 54% schema description coverage, the description partially compensates by naming the filter axes (district, cuisine, price, distance, open now), which maps onto district, cuisine, price_min/price_max, lat/lng/radius_m, and open_now. It adds no detail on the undocumented q, city, limit, offset, or coord_system params, and does not clarify that lat/lng/radius_m must be used together for distance filtering.

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 names a specific verb+resource (filtered restaurant search) and enumerates the filter dimensions it supports (district, cuisine, price, distance, open now), so the purpose is unambiguous. It fails to distinguish itself from the sibling ask_restaurants, which also concerns restaurant discovery, so it stops short of a 5.

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?

It states the condition under which to use the tool ('when filtering by district, cuisine, price, distance, open now'), which is real usage context. However, it offers no when-not guidance and never names ask_restaurants or get_restaurant as the alternative for conversational or single-lookup cases, leaving the agent to guess which sibling to pick.

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, and it delivers: anonymous submission, no key/auth required, and that it 'stores only the text you send' (a data-retention disclosure). It also describes the return shape (recorded plus optional try_now) and input constraints, which is solid behavioral context for a no-annotation 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 front-loaded with the trigger condition, then constraints, then return value, in a clear order. The bilingual duplication doubles the length, but each line pairs necessity-of-use, restrictions, and output without 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?

There is no output schema, so the description correctly explains the return values (recorded, plus try_now with a ready link and ask_restaurants args). Combined with usage conditions and content restrictions, an agent has enough to invoke it correctly, though the optional context fields could be justified more explicitly.

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 schema already documents all five parameters (need, impact, for_whom, platform, scenario). The description adds only the content restriction on the free-text field and doesn't clarify the roles of the optional context fields, so 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?

The description clearly frames this as a request/need submission channel: 'Use when this site lacks the data or capability you need; anonymous, no key, stores only the text you send.' It states the resource (a need submission) and the trigger condition, and distinguishes itself from data-retrieval siblings by naming ask_restaurants as the fallback for answerable questions.

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?

It gives an explicit when-to-use condition ('when this site lacks the data or capability you need') and implicitly excludes cases where existing data can answer, routing those to try_now with ask_restaurants args. Content restrictions (no URLs, emails, phone numbers) add practical usage boundaries, though it doesn't state when NOT to use it beyond the capability condition.

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