Mexican Payroll & Tax Calculator

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

With no annotations provided, the description carries the full burden. It discloses that the exemption is UMA-indexed and returns specific fields (gross, taxable, exempt, ISR, net, days), but it does not cover potential side effects, authentication needs, error handling, or constraints beyond the legal minimum days. Some behavioral context is given, but gaps remain.

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, front-loading the core purpose ('Compute a Mexican aguinaldo') and listing key details in a single sentence with clear separators. However, the list of outputs is somewhat run-on, and the imperative warnings add slightly to length, but overall 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 no output schema, the description adequately lists the return values (gross, taxable, exempt, ISR, net, days worked). It explains the legal minimum and UMA-indexed exemption, which are crucial for correct use. However, it does not describe the calculation logic or the meaning of days_worked in detail, leaving some gaps but sufficient for basic use.

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 parameters. The description adds minor context (e.g., 'Minimum 15 days by law' relates to aguinaldo_days default, and 'exemption is UMA-indexed per year' relates to the year parameter), but it does not significantly enhance understanding beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool computes a Mexican aguinaldo (year-end bonus) and lists the outputs (gross, exempt, taxable, ISR, net). The verb 'compute' and resource 'Mexican aguinaldo' are specific, and the sibling tools (finiquito, IMSS, ISR) are clearly different, making the purpose distinct and unambiguous.

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 aguinaldo calculation and includes a warning not to compute from memory, but it does not explicitly state when to use this tool versus the siblings (calc_finiquito, calc_imss, calc_isr) or provide any exclusions or prerequisites. Guidance is implicit rather than explicit.

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 adequately describes the computation and output breakdown but does not disclose behavioral traits such as whether the tool is read-only, any authentication needs, or rate limits. It assumes a simple compute operation.

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 that front-loads the purpose and lists components efficiently. Every sentence adds value, and there is no wasted 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 the tool's complexity (13 parameters, 4 required, no output schema), the description is quite complete, explaining the computed concepts and output structure. It could be slightly more explicit about the difference between finiquito and liquidación, but overall it provides sufficient 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 description coverage is 100%, so baseline is 3. The description does not add significant meaning beyond the schema for individual parameters; it focuses on the overall computation. It mentions output structure (gross/exempt/taxable, totals, ISR), which is helpful but not parameter-specific.

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 computing a Mexican finiquito/liquidación for resignation or unjustified dismissal, listing specific components like prorated christmas bonus, vacations, etc. It easily distinguishes from sibling tools (calc_aguinaldo, etc.) by focusing on severance calculations.

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 warns against computing from memory and notes that LFT bands, UMA exemptions, and SDI integration are table-driven, implying the tool should be used for accuracy. However, it does not provide explicit guidance on when to use alternatives or when not to use this 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?

With no annotations, the description fully bears the burden of transparency. It discloses that the computation is table-driven, that rt_premium is an input fraction, and that it returns a breakdown per branch. It does not mention side effects, but as a pure calculation tool, none are expected.

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 six sentences, each contributing important information: purpose, input options, warnings, and output summary. It is front-loaded and well-structured, though slightly verbose; a more concise phrasing could be used without losing clarity.

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 of the tool (8 parameters, no output schema), the description is fairly complete. It lists all return fields, covers input constraints, and warns about table-driven logic. It could mention error conditions or defaults, but overall it is adequate.

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 baseline is 3. The description adds value by explaining how parameters interact (e.g., seniority_years derives SDI, paid_in_january is for UMA boundary) and clarifies that rt_premium is a fraction, going beyond the individual schema descriptions.

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 specifies what the tool does: compute Mexican IMSS social-security contributions including SDI, SBC, and quotas. It distinguishes itself from siblings (calc_aguinaldo, calc_finiquito, calc_isr) by detailing its specific output and input requirements.

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 usage guidance, such as providing either seniority_years or explicit sdi, and warns against computing from memory. It does not explicitly contrast with siblings, but the context makes it clear that this tool is for IMSS calculations.

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 provided, so description carries full burden. It describes the tool as deterministic and lists return fields (tax, subsidy_applied, withholding, period, year), but doesn't mention error handling or edge cases. Adequate for a computation 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?

Two efficient sentences that front-load the purpose and key behavior, with no wasted words. 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?

Despite no output schema, description specifies returned fields. Tool is straightforward with 4 documented parameters; description covers purpose, usage guidance, and return values completely.

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 description adds limited parameter detail beyond the schema. It provides context about periods and official tables but doesn't enhance parameter understanding beyond what the schema already provides.

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 Mexican ISR withholding using official SAT tables, specifying the period (monthly/annual) and distinguishing it from sibling tools like calc_aguinaldo or calc_imss.

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 warns not to estimate ISR from memory and states that brackets/subsidy change yearly, directing the agent to use this deterministic tool instead of alternatives.

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