台灣勞健保勞退試算

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

Annotations indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds behavioral context by stating the calculation uses a specific formula, has no upper limit, and results are for reference only (not official). This is consistent with annotations and provides additional clarity beyond the structured hints.

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, well-structured sentence that includes the formula, rate, limitation, and disclaimer. Every part is essential and there is no wasted text.

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 (formula, parameters, caveats) and the presence of an output schema, the description covers the essential purpose, formula, and disclaimer. It could mention that the result is a numeric value, but the output schema likely handles that.

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 input schema already documents all parameters. The description does not add further parameter details but provides the overarching formula context, which is sufficient given the schema's completeness.

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 it calculates the employer supplementary premium (雇主補充保費) with a specific formula and rate (2.11%). It distinguishes itself from sibling tools like calculate_supplementary_premium by explicitly targeting employers.

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 context by stating it calculates the employer-side premium and includes a disclaimer that results are for reference only. However, it does not explicitly state when to use this tool versus alternatives or provide exclusion criteria.

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 indicate read-only and idempotent behavior. The description adds meaningful caveats that results are for reference only and not legally binding, enhancing transparency about limitations and official reliance.

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, well-structured paragraph that efficiently conveys all essential information without redundancy. Each sentence adds necessary detail, covering all three cases and the disclaimer.

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 (5 parameters, 1 required, output schema present), the description adequately explains input usage and calculation methods. It omits details about the output format, but the presence of an output schema mitigates this gap. The disclaimer about reference-only results adds necessary context.

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 100% of parameters with descriptions. The description adds value by explaining the calculation rules behind the enum values (e.g., formula for resident, 5% threshold for bonuses, 18%/6% for non-resident) and specifying when each parameter applies, going 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?

The description clearly states the tool computes income tax withholding (薪資所得扣繳稅額) and enumerates three specific categories (resident monthly salary, resident bonus, non-resident). It distinguishes itself from sibling tools like pension calculations or supplementary premium calculators by focusing solely on withholding.

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 each type (resident, residentBonus, nonResident) including rate details and conditions. However, it does not explicitly mention when not to use this tool or suggest alternatives, slightly limiting the 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 indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds that results are for reference only and not legal advice, but does not disclose any additional behavioral traits (e.g., no side effects, calculation-based). 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 sentence that front-loads the formula and key constraints. It is concise with no unnecessary words or repetition.

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?

The description covers the formula, caps, and disclaimers. With an output schema present and high schema coverage, it is mostly complete. It also references list_years for year parameter guidance. A minor gap is the lack of explanation about return values, but that is covered by the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 5 parameters. The description adds the formula but does not provide additional meaning per parameter beyond what is in the schema. 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 defines the tool's purpose: it calculates the old-age lump sum payment using the legal formula (average monthly insured salary × number of benefit months, with specific rules for years of service and post-60 caps). It distinguishes itself from sibling tools like 'calculate_old_age_pension' by specifying the lump sum 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?

The description provides no explicit guidance on when to use this tool vs. siblings. It does not mention alternatives like 'calculate_old_age_pension' or 'calculate_old_age_single_payment', leaving the agent to infer usage from the name alone.

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, indicating safety. The description supplements with formula details (±4% per year, max ±5 years) and a clear disclaimer that results are for reference only and not legal advice, adding behavioral context 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?

Two concise sentences: the first covers purpose and key formula details, the second provides necessary disclaimers. No wasted words, and critical information is front-loaded.

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 (not shown), the description appropriately focuses on eligibility, formula mechanics, and legal disclaimer. No additional context is needed for this calculation tool with rich annotations and schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all parameters have descriptions in the schema itself. The description does not add significant new meaning beyond the schema, only referencing the formula's adjustment mechanism. 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 explicitly states it calculates monthly old-age pension using legal formulas, including the two-option election and early/deferred adjustments. It clearly distinguishes from siblings like calculate_old_age_lump_sum (lump sum) and calculate_old_age_single_payment (single payment) by specifying '月領' (monthly).

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 for monthly pension calculations and includes the important eligibility condition (years < 15 are ineligible). However, it does not explicitly mention when to use this tool versus alternatives like lump sum or single payment.

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 readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the tool is safe and non-mutating. The description adds significant behavioral context beyond annotations: it details the exact formula and its components (e.g., base units per year, caps at 45 or 50 units), the applicability condition (insurance years before 1998), and a disclaimer that results are for reference only. This fully informs the agent of the tool's behavior and limitations.

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 consists of two sentences: the first conveys the core purpose and formula, the second provides a disclaimer. It is front-loaded with essential information. While the first sentence is somewhat long, it is still clear. There is no unnecessary verbosity, and every sentence adds value.

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 that the tool has an output schema (not shown but indicated), annotations, and full parameter coverage, the description is fairly complete. It explains the formula, applicability, and provides a disclaimer. The only minor gap is the lack of mention about rounding or precision of the result, but this is acceptable.

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 descriptions for all 6 parameters. The description adds overarching context by explaining how parameters map to the formula (e.g., preSixtyYears and postSixtyYears correspond to years before/after age 60). However, most parameter details (e.g., the 5-year cap on postSixtyYears) are already in the schema descriptions. The description does not provide substantial new meaning beyond what the schema already conveys.

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 calculates the old-age single payment using a specific formula ('基數制'), including the formula details. The name and title are in Chinese and match the description. It distinguishes from siblings like calculate_old_age_lump_sum by specifying the exact type of lump-sum calculation and its applicability to those with insurance years before 1998.

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 mentions it is applicable for those with insurance years before 1998 ('適用 98 年前已有保險年資者'), providing a clear context. However, it does not explicitly state when not to use this tool or suggest alternative tools (e.g., calculate_old_age_pension for those with newer insurance years). The disclaimer about reference only is present but does not guide selection.

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 indicate readOnlyHint=true and idempotentHint=true, so the tool is safe and idempotent. The description adds value by stating results are for reference only and do not constitute legal or accounting advice, setting appropriate expectations. It does not contradict 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, clear paragraph that efficiently conveys the tool's purpose and supported features. It is front-loaded with the main action and resource. Every sentence adds value, though it could be slightly more concise by omitting the disclaimer (which is useful but 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?

Given the tool's complexity (9 parameters, 1 required, output schema present), the description adequately covers the core functionality and supported scenarios. It mentions identity types, dependents, voluntary contributions, and part-time work. The disclaimer about reference-only is a good addition. It is sufficiently complete for an agent to understand usage.

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 documentation coverage is 100%, so the baseline is 3. The description does not add significant new meaning beyond what the parameter descriptions already provide; it merely summarizes the tool's features. No additional semantics are provided that would raise the 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 clearly states it calculates labor insurance, health insurance, pension, and occupational accident burdens for a Taiwan monthly salary. It uses specific verbs and resources and distinguishes from sibling tools like calculate_old_age_pension and calculate_income_tax_withholding by focusing on monthly payroll contributions.

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 this tool is for monthly payroll calculations and supports various identity types and part-time work, but it does not explicitly state when to use this tool versus alternatives or provide exclusions. The context of sibling tools provides some guidance, but the description itself lacks explicit usage directives.

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 indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds the specific calculation rules (e.g., 30-day basis for labor insurance, month-end attribution for health insurance) and the non-binding disclaimer. This adds some behavioral context beyond annotations, but given the strong annotation coverage, a score of 3 is appropriate.

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 extremely concise: two sentences plus a disclaimer. Every sentence serves a purpose—first states the core function and rules, second notes the reference-only nature. 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?

Given the complexity (11 parameters, output schema exists), the description provides sufficient high-level context: what the tool calculates, the underlying rules, and the authoritative reference. The output schema handles return values, so no further detail 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?

Schema description coverage is 100%, so all parameters have descriptions in the schema. The tool description does not repeat parameter details but provides an overview of the calculation logic. Baseline is 3, and the description adds no per-parameter value, so score remains 3.

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 computes prorated premiums for mid-month start or end (破月保費). It specifies the insurance types covered (勞保/職保/勞退 and 健保) and the calculation rules. This distinguishes it from siblings like calculate_old_age_pension or calculate_payroll, which handle other aspects.

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: use for mid-month start/end scenarios. It includes a disclaimer that results are for reference only. However, it does not explicitly state when not to use or mention alternatives among siblings, which would raise the score to 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 indicate readOnlyHint, idempotentHint, and destructiveHint=false. The description adds that the calculation uses a fixed rate of 2.11% with specific threshold and cap rules, and that the result is not binding legal advice. 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 few sentences covering core aspects: rate, rules for bonus vs other types, and a caveat. It is concise but could be slightly more structured by separating the rules more clearly. Still, it is 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?

Given the presence of an output schema (not shown but mentioned), return values are documented there. The description explains the input rules, thresholds, caps, and the non-binding nature. It is complete for the complexity of this calculation tool, with no missing context.

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 each parameter described. The description adds context beyond the schema, such as the bonus threshold being 4 times monthly insured salary and the single-payment cap of 10 million NTD. This helps the agent understand the calculation logic behind the parameters.

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 it calculates the second-generation national health insurance supplementary premium with a specific rate of 2.11%. It lists the income types (bonus, parttime, etc.) and explains the threshold rules, clearly distinguishing it from sibling tools like calculate_employer_supplementary_premium and calculate_income_tax_withholding.

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 when to use the tool for each income type (e.g., bonus tax on excess over 4x monthly insured salary, other types tax on single amount over threshold with a cap). It states the outcome is for reference only, not legal or accounting advice. However, it does not explicitly say when not to use or compare to 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?

Annotations already declare it read-only and non-destructive. The description adds context about the specific data returned (wage details) and its role in validation, complementing the 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?

Two concise sentences: the first lists outputs, the second provides usage guidance. No wasted words; front-loaded with 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?

For a read-only tool with no parameters and an output schema, the description fully covers what the tool does and when to use it. No gaps given the context.

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, and the description correctly implies no input is needed. It references valid year values without introducing ambiguity, meeting the baseline for param-free tools.

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 explicitly states the tool lists supported years, data versions, and basic wages. It distinguishes itself from sibling calculation tools by indicating its purpose as a preparatory step.

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 advises using this tool before calculations to confirm valid year values, providing clear context for when to use it. Since all siblings are calculation tools, no explicit exclusions are necessary.

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