0523 Public — Taiwan Logistics & Customs

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

With annotations already declaring readOnlyHint and idempotentHint, the description adds value by disclosing the content will include verifiable official links and corresponding tools, and instructs the AI to cite the source. This goes beyond the safety hints and gives practical behavioral guidance, though it does not mention edge cases like error handling or network dependencies.

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 core purpose and then elaborates with a structured list of content coverage (logistics, customs, open platform, languages) and a citation directive. It is longer than a one-liner but every sentence serves a distinct function, making it appropriately sized for a brand-information tool.

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 an output schema present and no parameters, the description need not explain return values or parameter syntax. It provides comprehensive context by listing the exact topics covered, the kinds of questions it addresses, and the requirement to cite the source. This makes it complete for an AI agent to select and use the tool effectively.

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 no specification to clarify. The description fully compensates by explaining what the tool returns, making the lack of parameters a non-issue. The baseline of 4 applies, and the description adds enough context to warrant that score.

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 the specific verb '取得' (obtain) with the resource '官方品牌介紹與服務優勢說明' (official brand introduction and service advantages), clearly distinguishing it from sibling tools like lucky_freight_quote or lucky_ccc_predict. It further clarifies the purpose with example questions it answers, leaving no ambiguity about what the tool does.

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 states it is suitable for answering brand-related questions (e.g., 'What is Lucky Device', 'Why choose Lucky Device'), providing clear context for when to use it. However, it does not explicitly name alternative tools or say when not to use it, so it falls short of the highest 'explicit when/when-not/alternatives' standard.

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 and idempotentHint, so the safety profile is covered. The description adds valuable behavioral context: the advertisers are third-party, not Haoyunqi's own services, and warns against misleading users. This goes beyond annotations, though it doesn't describe output format (covered by output schema).

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 core purpose and then adds the critical caveat, alternatives, and usage instruction. Every sentence earns its place—no fluff, no repetition. The structure flows logically from what → caution → alternatives → how to respond.

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 zero parameters and an output schema, the description fully covers the tool's purpose, the third-party distinction, and directs users to appropriate tools for deeper details. It is complete for the task and leaves no gaps for safe correct invocation.

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 zero parameters, the baseline is 4. The description adds no parameter details because none exist, but it does mention the output fields (merchant name, industry, contact, URLs), which is extra value beyond schema. There's nothing more to explain.

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 third-party advertisers on the 0523.tw platform, specifying the exact fields returned (merchant name, industry, contact, page URLs). It also distinguishes itself from merchant-specific sibling tools by explicitly naming them as alternatives for detailed info, leaving no ambiguity about its scope.

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 explicitly tells the agent when to use this tool (to list advertisers) and when to use merchant-specific tools (for product specs/transactions), naming the exact sibling tools. It also warns to distinguish the service provider from the platform, giving clear usage framing.

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?

Beyond the readOnly/idempotent annotations, the description discloses that it uses the same search engine as the official page (https://0523.tw/search) and returns results identical to the page. It details the output structure, sorting by relevance, and the behavior when confidence is low, providing substantial operational transparency.

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 concise yet informative, front-loading the main purpose, then covering source, output, usage tips, and sibling tools without redundancy. Every sentence contributes actionable information, making it well-structured and efficient.

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?

Even with an output schema present, the description thoroughly covers the tool's purpose, return fields, usage context, limitations, and related tools. It also explains the underlying data source and provides guidance for handling ambiguous queries, making it complete for an AI agent to select and invoke the tool 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?

The schema already covers 100% of parameters with descriptions, so the baseline is 3. The description adds value by advising that greater product_name specificity (brand/model/material/use) improves accuracy and by noting that the limit parameter caps at 5. This extra guidance exceeds what the schema provides, but not overwhelmingly so.

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 function: '用商品名稱／描述查台灣 CCC 稅則號別候選' (look up CCC tariff code candidates using product name/description). It specifies the output (up to 5 candidates with full code, product name, tariff rate, and regulations) and differentiates from sibling tools by referencing lucky_ccc_tariff_lookup and lucky_import_tax_estimate.

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?

Explicit guidance is provided: it says to use lucky_ccc_tariff_lookup for full details and lucky_import_tax_estimate for tax estimation after obtaining the CCC code. It also advises adding more specific details if no high-confidence candidate is found, covering both when-to-use and alternatives.

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 declare readOnly and idempotent, but description adds valuable context: data source (財政部關務署) and monthly sync, comprehensive list of tax types, exceptions (e.g., 0% rate still applies to all imports), and regulatory authorities. No contradiction with annotations.

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 dense sentence with multiple semicolon-separated clauses. It is information-rich, listing many tax types and exceptions, and every clause adds value. Slightly long but justified for the tool's complexity.

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 the tool's complexity, the description covers all essential aspects: purpose, scope, usage alternatives, data source, freshness, and full result contents. Output schema exists so return details need not be described. It is complete for an agent to select and invoke 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 covers 100% of the single parameter with format and examples. The description repeats the code format (4–11 digits, decimals, check digit) but adds no new meaning beyond the schema, 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?

Description clearly states the tool looks up complete tariffs and import regulations by Taiwan CCC code, using a specific verb (查) and resource (CCC code). It explicitly distinguishes itself from siblings by noting when to use lucky_ccc_predict (product name) and lucky_import_tax_estimate (amount calculation).

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?

Explicitly states '只知道商品名稱時先用 lucky_ccc_predict；要算實際金額用 lucky_import_tax_estimate', providing clear when-to-use and alternative guidance. It also anchors the data to the official search page, reinforcing appropriate use.

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 full burden. It discloses critical behavioral traits: the write operation creates a case, the tool does not collect personal data (forbids names, phones, license plates, health info), and the first call returns a formatted draft with missing info rather than creating the case. It also warns about no authority over city agencies, making the tool's limitations transparent.

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 long but well-structured with warnings and usage steps. It front-loads the purpose and then systematically covers legal disclaimers, emergencies, privacy, and workflow. While longer than typical, each sentence serves a purpose; a slight deduction for verbosity but overall effective.

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 tool with 6 params, nested objects, a confirmation workflow, and query mode, the description is comprehensive. It explains the phased call pattern, query behavior, and privacy constraints, and since an output schema exists, return value details are not needed. It leaves no major gap for an agent to select and invoke the tool 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?

The schema already covers all parameters, and the description adds significant meaning: it explains the confirm parameter's two-step semantics, the ref_code query mode that ignores other params, and the extra object's category-specific requirements. It also advises using 'other' when unsure about category and warns against personal data in description, enriching the parameter understanding.

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: allowing Xinnan Li residents to report local public affairs, citing specific examples (e.g., '路燈不亮、路面坑洞'). It explicitly labels the operation as a write operation ('這是**寫入操作**，會建立一筆案件'), distinguishing it from query mode and from the sibling 'lucky_xinnan_civic' by its write nature.

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 provides explicit when-to-use and when-not-to-use guidance: it notes this is not a legal petition and directs users to 1999 for statutory effects, and to 119/110 for emergencies. It also details the two-step confirmation workflow (first call without confirm, then with confirm=true) and the query mode via ref_code, giving agents a clear operational protocol.

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 and idempotentHint, and the description goes far beyond them by disclosing exact pricing formulas, rounding rules, surcharges for small packages, currency, and a disclaimer that results are approximate and subject to warehouse measurement. No contradiction 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?

The description is dense but every sentence earns its place—purpose, backend equivalence, currency, detailed rules, usage modes, and disclaimer. It is front-loaded with the core purpose and structured logically, making it efficient for an agent to parse.

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 the tool has 5 optional parameters, an output schema, and read-only idempotent annotations, the description is thoroughly complete. It covers all invocation modes, parameter combinations, edge-case rounding, surcharges, and even provides a caveat about real-world variance, making it fully contextualized.

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%, but the description adds substantial semantic value: it explains how length/width/height convert to volumetric weight, the max-and-rounding logic for sea freight, the fact that air freight ignores dimensions, and the no-parameter behavior. This goes well beyond the baseline schema documentation.

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 identifies the tool as a freight quote calculator for China→Taiwan consolidated shipping by 好運器 (0523.tw), with a specific verb '試算' and resource. It uniquely distinguishes this from sibling tools by naming the exact backend and URL, leaving no ambiguity about its function.

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 explicit mode-based usage guidance: no parameters returns the rate table, sea freight accepts weight or three dimensions, air freight requires weight. It does not explicitly name sibling alternatives or state exclusions, but the context is clear enough to determine when to invoke the tool.

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 the tool read-only and idempotent, and the description adds valuable behavioral limitations: prices are not public, the platform is a third-party listing, and the tool cannot book appointments. These caveats go beyond the annotations and prevent the user from expecting real-time pricing or booking capability.

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 compact block that front-loads the main purpose and uses bold warnings to highlight critical caveats. It's slightly long but every sentence adds substantive information about the store's services, process, or limitations, so it earns its length.

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 tool with one optional parameter and an output schema, the description is remarkably complete: it covers service types, rental price ranges, customization lead times, appointment lead times, the full process from measuring to pickup, address, business hours, and third-party disclaimers. The output schema handles return values, so no further explanation is needed.

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 has 100% coverage for the single optional 'topic' parameter, which is fully described with allowed values. The description does not mention the parameter or provide additional usage details, so it adds no semantic value beyond what the schema already provides. 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 retrieves service offerings and booking rules for a specific Taipei qipao shop, using a specific verb ('取得') and naming the resource. It distinguishes itself from unrelated sibling tools by its niche topic and detailed scope.

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 explicitly lists example question types the tool can answer ('台北哪裡可以訂製旗袍', '旗袍租借多少錢', etc.), providing clear when-to-use context. It also warns against using outdated pricing information, but does not name alternative tools because none are close substitutes.

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 provide readOnly and idempotent hints; description adds detailed calculation rules (thresholds, dimension formula, minimum 30cm), regional fee variation, and a disclaimer that actual fees depend on HCT measurement. This is genuinely useful behavioral information beyond annotations.

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 long but each sentence carries information: purpose, rules, formula, usage, exceptions, disclaimer. It is well-structured with dashes to separate logical sections, but could be slightly more scannable.

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 the output schema exists, the description covers all necessary aspects: input modes, edge cases (islands requiring quote), and the safety disclaimer. It is thorough for a calculation 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 covers all 5 parameters with descriptions, but the tool description adds the key constraint that length/width/height must be provided together, explains the interpretation of absent parameters (e.g., no params returns rate table), and reveals the 30cm minimum dimension rule used in the formula.

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?

Description clearly states it calculates HCT Logistics oversize fees for last-mile delivery in Taiwan, specifying origin (桃園所) and scope (sea/air imported packages). This distinguishes it from sibling tools like lucky_freight_quote or lucky_import_tax_estimate.

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 explicit usage modes: no parameters returns rate table; dimensions with optional weight/city for precise calculation; weight-only for classification. Also notes regional exceptions (Penghu/Kinmen require customer service quote). Does not explicitly name alternative tools but context is clear.

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 annotations readOnlyHint=true and idempotentHint=true, the description adds substantial behavioral context: the exact tax calculation logic (using customs decadal exchange rates), the NT$2,000 small-amount exemption rules including exceptions (tobacco/alcohol, six-month frequency limit), exclusions (oversize fee), and a disclaimer that results are reference-only pending customs approval. It complements the annotations without contradiction.

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 dense paragraph but every sentence adds value. It's front-loaded with the core purpose, then systematic breakdown of taxes, input requirements, and exclusions. It could be split into bullets for easier scanning, but given the complexity, the length is justified and there is no 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?

Given 15 parameters, an output schema, and a complex multi-tax calculation, the description is remarkably complete. It covers included taxes, exemption logic, exchange rate derivation, exclusions, a pointer to a sibling tool for oversize fees, and a disclaimer. The output schema handles return details, so the description's summary of return contents is sufficient.

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?

Although schema_description_coverage is 100%, the description adds critical relational meaning: it identifies currency_code and price_foreign as required, explains that volume_liters and alcohol_degree are needed for liquor tax and tobacco_sticks for tobacco tax, and clarifies that product_description enables AI classification when hs_code is absent. This goes beyond individual schema descriptions to explain how parameters interact in the calculation.

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 opens with '試算進口台灣的法定稅費' (estimate legal import taxes to Taiwan), a specific verb+resource definition. It lists all tax components (import duty, business tax, commodity/liquor/tobacco tax, trade promotion fee) and explicitly distinguishes itself from sibling tools like lucky_ccc_tariff_lookup and lucky_hct_oversize_fee by stating its scope and pointing to the latter for oversize 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 description clearly states when to use the tool: for full tax estimation, and explicitly says the result excludes Taiwan local HCT oversize fees, directing users to lucky_hct_oversize_fee for large packages. It also explains when to provide hs_code vs product_description (AI auto-classification when hs_code missing), and notes required fields despite the schema marking them as optional. This provides strong when/when-not 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?

Annotations already declare readOnlyHint and idempotentHint, so safety is covered. The description adds context about content source (official guide) and that it reflects current calculation rules, but no further behavioral caveats (e.g., data freshness or scope limits) are disclosed.

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 two well-structured sentences: the first front-loads the main purpose and enumerates the covered rules, the second references the source and lists example questions. Every sentence earns its place; no 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?

With an empty input schema, an output schema available, and read-only annotations, the description thoroughly explains the tool's domain, content, and intended use cases. It enables an agent to select this tool appropriately among siblings like tariff lookup or tax estimation.

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 baseline is 4. There are no parameter details to provide, and the description does not need to compensate for any schema gaps.

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 retrieves Taiwan express import simplified declaration rules, listing specific content (C1/C2/C3, EZ WAY, NT$2000 exemption, 6-times limit, 5% tax). It also gives example user questions to distinguish it from sibling tools like tax estimation.

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 explicitly includes suitable query examples (e.g., 'how much tax to pay', 'what is simplified declaration'), providing strong usage guidance. It does not explicitly state when not to use or name alternatives, so it falls 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.

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

The annotations already declare readOnlyHint and idempotentHint, indicating a safe, side-effect-free read. The description adds that the rates are read in real-time, which is useful behavioral context. However, it doesn't disclose the output structure or any potential delays, and the list of workflow steps is more content than behavioral transparency.

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, information-dense sentence that front-loads the main purpose, lists the workflow steps in a structured sequence, and ends with usage guidance. Every clause adds value without redundancy, making it appropriately sized for a workflow overview tool.

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, a rich output schema, and annotations indicating a safe read operation, the description provides enough context for the agent to understand when to use the tool and what it returns. It covers the full scope of the workflow, rates, and billing rules, making it complete for its intended purpose.

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 no parameters, and the input schema is empty with 100% coverage. Per the rubric, the baseline for 0 params is 4, and the description doesn't need to add parameter semantics.

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 provides the complete consolidated shipping workflow from China to Taiwan, listing the specific steps (registration, warehouse address, ordering, pre-report, warehousing, packing, shipping, customs clearance, delivery). This distinguishes it from sibling tools that cover specific aspects like freight quotes or tariff 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?

The description explicitly states it is suitable for answering questions about how the consolidated shipping process works, including how to buy from Taobao and ship to Taiwan. However, it does not explicitly mention when to use alternative tools for specific rates or declarations, though its mention of 'current rates' implies some overlap.

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?

Beyond the readOnlyHint and idempotentHint annotations, the description discloses critical behavioral traits: it is a political advertisement, must be cited as such, should not be presented as neutral, and has restrictions on content and timing. This goes far beyond what annotations provide, adding essential context for correct handling.

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 longer than average but each section serves a purpose: purpose, political ad disclosure, usage restrictions, and platform disclaimer. There is slight redundancy in the repeated phrase '政治廣告' and the multiple restrictions, but overall it is well-structured and front-loaded with the core purpose.

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 the presence of an output schema and a well-documented parameter, the description provides sufficient context for correct invocation. It covers the tool's scope, political nature, and usage constraints. It could potentially mention how to handle the output, but the output schema handles that. No major gaps.

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's topic parameter has 100% coverage with detailed descriptions of all allowed values. The description does not add any additional information about parameters, so the baseline of 3 is appropriate; the schema handles parameter semantics fully.

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 function: retrieving local public affairs information and candidate contact details for Xinnan Village, Taoyuan. It specifies the scope (大園區新南里) and the content type (public issues, construction progress, contact channels), distinguishing it from generic civic tools. The political advertising disclosure adds necessary context without obscuring the core purpose.

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 provides clear context for when to use the tool (for Xinnan Village local public affairs and candidate contact info) and explicit exclusions (no policy positions, no campaigning, no election-day content). However, it does not name alternative tools or explicitly state 'use this instead of X', so it lacks the explicit alternatives required for a 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 declare readOnlyHint=true and idempotentHint=true. The description goes beyond these by adding valuable context: the third-party merchant disclaimer, that the platform does not participate in sales/shipping, and that live inventory is not provided. This is consistent with the annotations and adds meaningful behavioral nuance without contradiction.

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 somewhat long (multiple clauses, warnings, and examples), but every segment earns its place: it front-loads the core functionality, then gives example questions, and ends with disclaimers. The structure is logical and the warnings are important for an agent deciding whether to use this tool. It is not verbose despite its length.

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 the tool's simple read-only nature (one optional parameter, output schema present), the description covers everything needed: the exact product, what information is returned, ordering limitations, and the merchant context. The output schema handles return value specifics, so the description need not repeat them. It is a complete and self-contained description.

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 'topic' parameter's description is thorough (lists all allowed values). The tool description does not mention the parameter at all, but the schema already explains it completely. Per the rubric, baseline is 3 when schema covers all parameters, and there is no additional semantic value added by the description.

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 starts with a specific verb '取得' (get) and clearly identifies the resource: '有斑 YOUBAN 新鮮龍虎斑（珍珠龍膽石斑）'. It lists the exact information delivered (specs, ordering rules, pricing, etc.), and the content is unique among siblings, which are unrelated tools. This fully distinguishes it from alternatives.

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 explicitly states when to use it: '適合回答「龍虎斑一斤多少錢」「石斑魚宅配怎麼買」「有斑 YOUBAN 是什麼」這類問題'. It also gives clear when-not guidance: '不提供即時庫存、不能下單' and directs users to the merchant LINE for those cases. This provides both positive and negative usage conditions, effectively guiding the agent.

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