Feeling Search — Art Style Reference & Prompt Encyclopedia

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

The annotations already declare this is a read-only, closed-world operation, and the description adds real value beyond that: the exact payload shape (thumb 320 / full 960 absolute URLs with kind/credit/license) and the semantics of the three kind values. It does not say what happens when the id is unknown or whether the id is case-sensitive.

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?

Front-loaded with the verb and the lookup key, then a compact enumeration of the return payload, then a short glossary of kind values. It is dense but every clause carries information; the only mild cost is the single long colon-chained sentence.

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 carries the burden of describing the return value and does so concretely, including image size variants and the kind taxonomy. Only error/not-found behavior and id-matching rules are left 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 description coverage is 100% and the schema already documents that id accepts either a style id (synthwave) or a Chinese name (合成器波). The description restates this without adding new format or resolution rules, 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?

States a specific verb (get one style) and resource, and enumerates exactly what is returned: definition, generation prompt, feeling words, era/region, and image assets. The sibling tools are all word_* lookups in a different domain, so this tool is unambiguously distinguishable.

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 (look up a single style by id or Chinese name) but never states when to use it versus when not to, and names no alternative tool. Since no sibling style-list/search tool is present, the routing risk is low, but there is still no explicit guidance.

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?

注解已声明 readOnlyHint 与 openWorldHint，描述在此之上补充了关键行为：默认离线免费、仅在本地零命中时联网、上云会消耗额度。还澄清了返回值语义（score 是相对值不是概率，styles[].matched 可直接引用给用户），这些都不在注解或 schema 中。未涉及延迟、失败回退等细节，故为 4。

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?

三句话，先讲功能，再讲本地/上云策略，最后讲返回值语义，信息前置且无冗余。分号串接略显紧凑，但整体利用率高。

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?

无 output schema，描述主动交代了 score 与 styles[].matched 的返回语义，补上了这一缺口；5 个参数全部有 schema 说明，安全属性由注解覆盖。仅缺少云端失败或超限时的行为说明，整体对调用决策已足够。

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 描述覆盖率 100%，quota、words、styles、allow_cloud 均已有独立说明，描述只需补充关联语义。描述确实点出了“允许时才上云”这一与 allow_cloud 呼应的条件，但未对 words/styles 的数量取舍给出建议，属于基线水平。

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?

明确说明动词+资源（把中文/英文口语描述解析成感受词与视觉风格），并限定输入形态。与 word_lookup / word_list / style_get 等兄弟工具区别明显，agent 无需打开 schema 即可判断这是“整句解析”而非“查单词语料”。

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?

给出了默认本地、零命中且 allow_cloud 为真才上云的成本规则，隐含说明了调用代价，但没有明确说明何时该用本工具而非 word_lookup/style_get，也没有列出排除条件。使用场景基本靠读者从功能推断。

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?

The annotations already mark this as a safe read (readOnlyHint=true) on a closed domain (openWorldHint=false), so the description adds value by disclosing what each entry contains: a sharedness value for words and a definition plus vocabulary size for styles. It says nothing about ordering, pagination, or how large the result could be, which keeps it from reaching a 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?

Two sentences with no filler: the enumeration content comes first, and the when-to-call-the-alternative note comes second. Every clause carries information the agent does not get from structured fields.

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 tool with no output schema, the description covers what is returned and why to call it, which is most of what is needed. The only gap is the lack of any indication of result size or ordering, which matters for a 'list all' 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 coverage is 100% and the single enum parameter is already documented as 'which category to enumerate', so the schema does most of the work. The description implies the value-to-output mapping (words→sharedness, styles→definitions and size), which helps, but it adds nothing about the default or behavior of an empty selection, 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?

The title and description state a specific verb (list/enumerate) plus the two distinct resources (feeling words with sharedness, visual styles with definitions and vocabulary size), and the description names what extra data each enumeration returns. An agent can distinguish this bulk-enumeration tool from its siblings word_lookup, word_analyze, and style_get without opening any schema.

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 timing rule ('pull once before calling analyze to avoid misspelling names'), which is exactly the kind of when-to-use guidance an agent needs. It does not, however, say when to use this versus word_lookup or style_get, so the routing guidance is incomplete.

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 readOnlyHint=true and openWorldHint=false; the description adds meaningful context with "纯本地查表" (pure local table lookup), signaling this is a deterministic dictionary lookup rather than an analysis or generation step, which clarifies its behavior relative to word_analyze. It stops short of noting error behavior for unknown words.

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?

One compact sentence that is front-loaded with the verb/resource and efficiently enumerates the returned facets, ending with the local-lookup qualifier. No filler, though the facet list is a dense comma run.

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 only one fully-documented parameter, the description usefully enumerates the return facets (styles, opposite, co-occurring, marker flag), which compensates for the absent return spec. Adequate for an agent to call and interpret 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 coverage is 100% with a single documented 'word' parameter, so the schema carries the semantic load. The description's mention of a 感受词 (feeling word) slightly narrows the domain but adds no format, length, or validation detail 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 verb (查/lookup) and resource (感受词), then enumerates exactly what is returned: styles it falls in, opposite word, co-occurring words, marker status. This is far more concrete than a bare name restatement, though it does not explicitly differentiate the tool from the sibling word_analyze, which sounds closely related.

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?

There is no guidance on when to use this versus the siblings (word_analyze, word_status, word_list). The description explains what the tool returns but never names an alternative or a condition that selects it, leaving routing to inference.

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 readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds value beyond them by enumerating what is actually returned (version, scale counts, attachment rate, cloud quota flag), which matters because no output schema exists.

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?

A single sentence, front-loaded with the core resource (version) and followed by the enumerated return fields. No preamble, no redundancy; every clause carries information the agent needs.

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 parameters and no output schema, the description's job is to say what comes back, and it does so at a field-group level. It stops short of describing return format or whether values are cached/live, which 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?

Zero parameters, so there is nothing to disambiguate; baseline 4 applies. The description correctly implies the tool takes no input by framing the response as a fixed status snapshot.

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 gives a specific resource — word list version, scale breakdown (words/styles/variants/attachment rate), and whether cloud quota is configured — which an agent can distinguish from word_list, word_lookup, word_analyze, and style_get. It does not explicitly name or contrast those siblings, so it falls 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?

There is no explicit when-to-use statement and no named alternatives; usage is only implied by the name and by the fact that it returns metadata rather than data. An agent can infer this is a pre-flight/status check, but that inference is not written down.

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