網紅開團合規工具箱

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

With no annotations, the description carries the full behavioral burden, and it does disclose the computation model (10% withholding + 2.11% supplementary premium) and the return value (實拿金額). What remains undisclosed is how the two income kinds alter the rates and whether any edge cases or limits apply.

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 front-loaded sentence that packs the purpose, the two rate components, and the output into 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 2-parameter calculator with no output schema and no annotations, the description covers the output semantics and the rate logic adequately, but leaves the pivotal 'kind' parameter and the 9A/92 distinction entirely unexplained.

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 the description never mentions the parameters. Critically, the 'kind' enum (9A / 92) is unexplained, yet these codes almost certainly select different withholding regimes, so the agent cannot tell which to pass. 'amount' is self-evident but the enum gap is substantial.

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 (試算/withholding calculation) and resource (網紅業配收入扣繳), and even names the constituent rates (10% 執行業務所得扣繳, 2.11% 二代健保). It is easily distinguished from siblings like calc_group_buy_profit or platform_fees.

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 scenario is implied by the phrase 網紅業配收入 (influencer sponsorship income), so an agent can infer when it applies. However, there is no explicit when-to-use statement, no mention of when not to use it, and no routing to or away 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?

No annotations are provided, so the description carries the full burden. It does disclose the computation model (which fees are deducted) and the returned metrics, but never states that this is a stateless, non-mutating calculation, nor how defaults are applied for the many optional parameters. Adequate but incomplete for an unannotated 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?

A single front-loaded sentence that packs the deduction list and the return values without filler. Slightly dense, but every clause contributes and nothing is wasted.

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 usefully names the return values (net profit per unit, gross margin, break-even price, target-margin price), which is a real contribution. However, for an 8-parameter tool with 38% schema coverage and no annotations, the meaning of qty, price and cost and the default behavior for optional fees remain unaddressed.

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 only 38% (ship, target, commission documented), so the description must compensate. It adds meaning for tax (營業稅), platform commission (蝦皮等), shipping, and 分潤, but says nothing about qty, price, cost semantics, or the missing 金流費 input, leaving several parameters ambiguous.

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 (pricing/profit simulation for group-buy and influencer direct-purchase scenarios) and enumerates the cost components deducted, which clearly separates it from lookup-style siblings like platform_fees or calc_creator_withholding. It does not name those siblings explicitly, 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?

The scenario scope (團購、網紅直購) implies when the tool applies, but there is no explicit when-to-use/when-not-to-use guidance and no mention of any alternative tool such as platform_fees or calc_creator_withholding. Usage is inferable but not directed.

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. It usefully discloses the return payload (hit words, risk level, penalties, suggested wording), which tells the agent the tool is a read-only analysis rather than a mutation, but it says nothing about limits, permissions, or whether the submitted text is stored.

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 front-loaded sentence gives the action, the scope, and the return payload with no wasted clauses. Nothing is duplicated or padded.

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, the description does the important work of naming what comes back (命中詞、風險等級、罰則、可用說法), so an agent knows the shape of the result. It is only missing input-format expectations and edge conditions.

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 neither parameter is documented in the schema. The description partially compensates by naming the subject matter (食品/化粧品廣告文案), which conceptually maps to the text and food/cosmetic enum parameters, but it never states that 'text' is the ad copy or that category must be one of two literal values.

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 (檢查) and resource (台灣食品或化粧品廣告文案) plus the exact violation domain (醫療效能、誇大不實的違規詞), which is easy to separate from tax, supplier, or fee siblings. It stops short of explicitly naming a sibling (e.g., endorsement_rules) as the alternative for endorsement-specific disputes.

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?

Usage is implied by the scope sentence: you use it on food/cosmetic ad copy you want screened for regulatory risk. There is no explicit when-not-to-use case and no routing to endorsement_rules or listing_checklist for overlapping compliance questions.

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. It usefully discloses the underlying rule thresholds (goods 100k, services 50k) that drive the verdict, but says nothing about permissions, whether the call is read-only, or how the registration/tax-rate result is returned.

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 dense sentence that front-loads the governing criteria before the verdict it produces. No filler, though the embedded threshold detail makes it slightly heavy.

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, no output schema, and 0% schema coverage, the description covers the decision logic but leaves the response shape (registration flag vs. tax rate value) and error/edge behavior unstated.

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% for two parameters. The description implicitly maps 貨物/勞務 to the type enum and 當月 to the monthly figure, which adds some meaning, but it does not clarify units (NTD), nor what happens when the optional type parameter is omitted.

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+resource: it determines whether an online seller must register for a tax ID and what tax rate applies for the month. The domain (Taiwan business tax thresholds) is distinct from siblings like platform_fees or calc_group_buy_profit, though it never names an alternative for comparison.

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?

Usage context is implied — online sellers evaluating a given month's sales against the 114-year threshold — but there is no explicit when-to-use/when-not guidance or named alternative tool for related determinations.

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 of behavioral disclosure. It only lists content topics and says nothing about whether the tool is read-only, what form the output takes, or any side effects, which is a complete omission of behavioral traits.

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, compact sentence that lists the relevant subtopics without filler. It is concise and appropriately sized for a simple reference tool, though it lacks a clear leading action verb.

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 no output schema and no annotations, the description should explain what the tool returns or how it behaves, but it does not. It provides a topic scope only, leaving an agent without enough context to invoke it confidently.

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 there are no parameter semantics to describe. The baseline score of 4 applies, as the schema already reflects the empty input.

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 regulatory domain (Taiwan FTC endorsement advertising rules) and its subtopics, but it is a noun phrase with no action verb, so it does not clearly state what the tool does (retrieve, check, summarize). It distinguishes the subject matter from siblings like check_ad_claims, but leaves the operation ambiguous.

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?

No guidance is given on when to use this tool versus alternatives such as check_ad_claims or listing_checklist. It neither states context nor exclusions, so an agent must infer usage entirely.

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 discloses almost nothing beyond the purpose sentence: no indication of whether this mutates state, requires permissions, or how results are returned. For an unannotated tool the agent is left to assume it is a safe read.

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 clauses with the purpose front-loaded and the parameter enumeration second; nothing is padded. The value list is dense but useful rather than wasteful.

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-optional-parameter checklist tool, the description supplies the purpose, the trigger moment, and the valid category set, with no output schema needed to explain returns. The remaining gap is the multi-select encoding into a string parameter, which is a minor but real omission.

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 0% and the single 'categories' property has no type-level detail, so the description is the only source of meaning — it names the six allowable values (food, cosmetic, electric, toy, medical, general) and notes multi-select. It does not explain how to encode multiple values into the string type (delimiter, array, etc.), and the empty default (0 required) is unaddressed.

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+resource in context: a compliance checklist run before a group-buy listing goes live (開團上架前合規清單). This is clearly distinguishable from sibling calculators and lookup tools. It stops short of explicitly differentiating from check_ad_claims or check_tax_registration, which are also compliance checks.

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 phrasing '上架前' (before listing) implies the usage moment — pre-publication compliance review — which is enough to infer when to call it. However, it names no alternatives and gives no explicit when-not guidance relative to the overlapping compliance siblings.

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 meaningful behavior: it validates the 統一編號 checksum and pulls data from the 經濟部 (Ministry of Economic Affairs) registry, and it lists the fields returned. It does not, however, state read-only/auth/rate-limit behavior or failure modes.

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 compact sentence that front-loads the verb and resource and then lists outputs; essentially no waste. It stops short of five only because it packs no usage or parameter disambiguation into that brevity.

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 lookup tool with no output schema and no annotations, it covers the return side reasonably by naming the returned fields, but leaves the input side under-specified: two 0%-documented parameters and no explanation of how ban and name relate.

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%, so the description must compensate and largely does not. It implies the tax-ID parameter via the checksum mention (ban/統一編號), but says nothing about the 'name' parameter, whether the two are alternatives, or that both are optional.

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/look up) and resource (台灣公司 Taiwan companies), and enumerates the concrete outputs: tax-ID checksum verification plus Ministry of Economic Affairs registration status, representative, capital, and address. It is clear on its own, but does not differentiate from siblings such as check_tax_registration, which overlaps on tax-ID territory.

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 or when-not-to-use guidance, and no mention of the similarly scoped sibling check_tax_registration. An agent must infer the usage context (supplier/company validation) purely from the name and description.

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, and it does disclose scope: only Shopee (general sellers and Mall), only 2026 rates, and a comparison against self-hosted sites. It does not state that this is a read-only/static reference, nor what form the answer takes, but for a zero-parameter informational tool the risk surface is small.

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, front-loaded sentence that states platform, seller categories, year, and the comparison baseline with no 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?

No output schema exists, yet for a no-parameter reference tool the scope statement (which platforms, which year, what is compared) is nearly sufficient. It could additionally note the currency/units or that other platforms are out of scope, but nothing critical is missing.

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 takes zero parameters, so per the baseline a 4 applies. There is nothing for the description to clarify beyond the resource scope it already names.

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 resource (Taiwan e-commerce platform commission and payment-processing rates for Shopee general sellers and Shopee Mall) and an explicit comparison target (self-hosted official website). It clearly differentiates itself from the calculation/checker siblings, though it uses no explicit verb (e.g., 'look up' or 'compare').

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 no when-to-use guidance, no prerequisites, and never names an alternative sibling. An agent must infer from the title alone that this is a reference-lookup tool rather than one of the adjacent calculators.

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