Netwise Paycheck Calculator

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

The annotations already declare this as a read-only, idempotent, non-destructive, closed-world operation, so the safety profile is covered. The description adds useful behavioral context by stating what is returned (annual salary, gross per check, hourly equivalent when hours_per_week is supplied, and full breakdown) and by ruling out bonus/supplemental wage gross-ups. It does not describe iteration or method, but that is not essential for a safe calculation 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?

The description front-loads the usage trigger, then explains the calculation, return values, and scope exclusion in three efficient sentences. Every sentence contributes distinct information and there is 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?

Given the 23-parameter schema with full descriptions, an output schema, and clear read-only annotations, the description covers purpose, usage, return shape, and exclusions well enough for an agent to call it correctly. No essential calling context 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?

Schema description coverage is 100%, so every parameter is already documented in the input schema. The description reinforces a few semantics through examples (state, monthly/biweekly targets) and mentions the condition for hourly equivalent (hours_per_week is given), but adds only marginal meaning beyond the rich 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 states a specific reverse-calculation verb and resource: solving for the gross salary or hourly rate that produces a target take-home pay. It anchors this with two concrete natural-language examples and explicitly scopes the calculation to 2026 payroll rules, making its niche immediately distinguishable from calculate_paycheck.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear when-to-use trigger (the user knows the take-home and asks what salary or rate they need) and an explicit when-not scope exclusion (bonuses and supplemental wages). It also references calculate_paycheck as the source of the same 2026 rules, but does not explicitly name it as the tool to choose for forward gross-to-net calculations or mention compare_paychecks.

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 establish readOnlyHint, idempotentHint, non-destructive behavior, and closed-world scope. The description adds substantive behavioral context: the exact tax methodology, pre-tax deductions handled, output artifacts (PDF estimate and CSV with one row per paycheck), and explicit non-goals such as not running payroll or filing tax returns.

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 usage triggers and then covers computations, outputs, and exclusions. It is appropriately sized for a complex 28-parameter tax calculator, though the first sentence is a long run-on with repetitive example phrasing.

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 full input schema, existing output schema, and safety annotations, the description is complete enough for an agent to understand when to call it, what it computes, what it returns, and what it does not do. No critical operational detail 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?

Schema description coverage is 100%, so all 28 parameters are already documented with examples and constraints. The description adds useful query examples that map to salary, state, and hourly inputs, but does not provide parameter semantics beyond what the schema already supplies.

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: computing take-home pay from salary, hourly wage, or gross pay, including federal/state withholding and deductions. It clearly distinguishes the tool from payroll processing and pay-stub generation, but it does not explicitly distinguish it from sibling tools like calculate_gross_up or compare_paychecks.

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 triggering user questions such as 'how much is my paycheck after taxes' and '85k salary after taxes in California,' along with exclusions like not for pay stubs or proof of income. It lacks explicit routing to sibling alternatives, so it falls short of a full 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?

Goes beyond the read-only/idempotent annotations by disclosing the inputs' merge contract (b holds only changed fields), naming the returned artifacts (per-check and per-year breakdowns, difference, PDF and CSV), and bounding scope. It does not mention error behavior or limits on the comparison, but the trait coverage is otherwise strong.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the use case, then the input rule, then outputs, then exclusions — a sensible order with no filler. The opening sentence is long because it packs in several example phrasings, which slightly blunts scannability.

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 two-object, deeply nested tool with an output schema, the description supplies everything needed to invoke it correctly: what to pass, how b relates to a, what comes back, and what the tool refuses to do. Return-value detail can safely be left to 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 baseline is 3. The description still adds real value by stating the split of labor between a and b ('give scenario a in full and scenario b with only the fields that change, everything else is copied from a'), which tells the agent how to construct the payload rather than just what each field means.

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 and resource ('compare take-home pay for two US paycheck scenarios in 2026 side by side') and immediately grounds it in recognizable user phrasings like state-to-state job offers and 401k changes. It is clearly distinguishable from calculate_paycheck by the two-scenario framing.

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?

Gives concrete triggering utterances ('should I take the job in Texas or California after taxes', raise, pay frequency change) and explicitly excludes out-of-scope uses: 'Does not compare cost of living, benefits, or run payroll.' Little is left to inference.

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