Tools Berry Paycheck

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

With no annotations, the description must disclose behavioral traits. It does mention the ranking and gap output, but it does not disclose calculation assumptions (e.g., which taxes are included, use of standard deductions) or limitations. This is moderately transparent but leaves room for ambiguity.

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 immediately conveys the tool's purpose and output format. It contains no filler or redundant wording, making it highly concise and well-structured.

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 three parameters and no output schema, the description is fairly complete: it explains the output ranking and gap, and the schema covers parameter details. While it lacks notes on tax assumptions, this is not critical for selecting or invoking 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?

Schema description coverage is 100%, so the baseline is 3. The description does not add parameter-specific meaning beyond 'same salary' and 'several states,' both of which are already evident from the schema's property descriptions. No extra semantics are provided.

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 exactly what the tool does: compares net pay on the same salary across multiple states, and specifies the output as a best-first ranking with gap to the best. This clearly distinguishes it from sibling tools like compute_take_home (single state) and get_state_rates (rates only).

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 tool's use case is implied by its name and description—comparing take-home across several states—but it does not explicitly mention when to use it instead of siblings like compute_take_home or get_state_rates. No exclusion criteria or conditional guidance is provided.

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

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

No annotations are provided, so the description carries the full burden. It discloses key behavioral details: the flat 22% federal rate, the 37% rate above $1,000,000, and that state treatment can be flat, aggregate/regular, or none. However, it doesn't explain how the calculation handles edge cases, what assumptions are made (e.g., default filing status), or what the result looks like. It adds useful rate context but leaves computational behavior partially opaque.

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 efficient sentence that front-loads the main purpose and lists the key components. It is not padded, though the parenthetical about the 37% threshold could be seen as slightly dense. Overall, it is appropriately sized.

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 should ideally say what the result contains (e.g., breakdown of federal, state, and FICA amounts). It mentions the components but not the output format. With 5 parameters and no annotations, more behavioral context could be provided, but it is adequate for a calculator tool. The description covers the core scope but misses details on return values and computational assumptions.

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, including formats, defaults, and the effect of earlierBonuses on the $1M threshold. The description doesn't add parameter-level detail beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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 computational purpose: what is withheld from a bonus, broken down into federal supplemental rate, state supplemental treatment, and FICA. This is clear and distinctive. It doesn't explicitly differentiate from sibling tools like compute_take_home, but the scope (bonus withholding) is specific enough to distinguish the intent.

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

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

There is no explicit when-to-use or when-not-to-use guidance, nor are alternatives named. The agent must infer that this is for bonus withholding calculations, but the description doesn't say when to prefer this over compute_take_home or how it relates to compare_states. No exclusions or prerequisites are mentioned.

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 transparency burden. It discloses the components calculated (federal/state taxes, Social Security, Medicare, state payroll programs) and output frequencies, but it does not disclose assumptions like the use of standard deductions, whether pre-tax deductions are ignored, or that results are estimates. This is a meaningful gap for a 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 is a single, well-structured sentence that front-loads the core purpose ('Full 2026 paycheck breakdown') and lists outputs efficiently. Every word adds value, with 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 the lack of an output schema, the description does a good job enumerating the net pay frequencies and tax components. However, it is slightly unclear what 'state payroll programs' refers to, and it does not explicitly mention that the filingStatus parameter affects state tax calculations, though that is implied by the 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 the schema already documents all three parameters. The description does not add any parameter-specific meaning beyond what the schema provides, so a baseline score 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 uses a specific verb ('compute') and resource ('take-home pay'), and explicitly lists the components and output frequencies. It clearly distinguishes from sibling tools like compare_states (which compares states) and get_state_rates (which only provides rates) by focusing on a single state's full paycheck breakdown.

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 phrase 'in one state' clearly implies this tool is for calculating take-home pay for a single state, differentiating it from comparing states. However, it does not explicitly mention alternatives or when not to use it, so it stops 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?

With no annotations provided, the description carries the full burden. It adds value by listing the contents of the schedule, but it does not disclose side effects (likely a read-only operation), error behavior, state coverage, or any quirks such as how disputed or missing rates are handled. It falls short of fully transparent but is not misleading.

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 is front-loaded with the core subject and efficiently lists the contained elements. No unnecessary words or repetition. It earns its place entirely.

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 main outputs but lacks details about the structure of the response (e.g., how bracket ladders are represented), potential edge cases (unknown state), or whether the data is for all states. Given the absence of an output schema, more specificity would be helpful, but the description is adequate for a straightforward retrieval 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?

The input schema has 100% coverage with detailed descriptions for both parameters (state formats, filingStatus defaults and coverage). The description adds no additional parameter semantics, so it does not exceed the baseline provided by 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 identifies the tool as providing a state's 2026 tax schedule, enumerating key components (flat rate/bracket ladder, standard deduction, payroll programs, bonus method, statutory source). This distinguishes it from sibling tools like compute_bonus_withholding and compute_take_home, which are computation tools. However, it lacks an explicit verb (e.g., 'retrieves') and relies on the name for the action.

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 that this tool is used to fetch rate schedule data, as opposed to computing withholding or take-home pay. It does not explicitly state when to use this instead of siblings, nor does it mention any exclusions or prerequisites. The guidance is implicit through content but not made explicit.

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