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

With no annotations present, the description carries the full behavioral disclosure burden and handles it well: it states the operation is 'deterministic, idempotent calculation with zero external side effects', names the pricing source, and details what the return includes. It also quantifies cache discounts up to 90% and batch discounts at 50%.

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 purpose statement is front-loaded, followed by compact behavior and usage-guideline paragraphs. Every sentence earns its place, with no filler or 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?

Since there is no output schema, the description clearly tells the caller what to expect: a cost comparison matrix, cheapest-model recommendation, cache savings, and cost multiples. Scope, model coverage, behavioral guarantees, and routing guidance are all present, making the definition self-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?

Schema coverage for all four parameters is already 100%, so the baseline is 3. The description adds useful context beyond the schema by clarifying pricing units ('per million input/output tokens') and giving quantitative discount context that maps to isBatch and cacheHitRatio, though it does not individually redefine each parameter.

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 a specific verb and resource: 'Calculate multi-provider LLM API inference costs...' and enumerates the model families covered. It also distinguishes itself from siblings by explicitly saying it is not for general cloud bandwidth costs and naming the correct alternative tool.

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 conditions such as 'budgeting AI agent inference costs' and 'evaluating LLM providers', plus a when-not-to-use condition with the named alternative cloud_egress_finops. This is strong, unambiguous routing guidance for an agent.

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 disclosure burden. It explicitly discloses deterministic, idempotent behavior with zero external side effects, provides the exact gross-up formula, and documents the 183-day high-risk alert trigger. It is slightly less explicit about the exact output shape, but core behavior is well covered.

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?

Purpose is front-loaded, and the description is neatly split into Behavior and Usage Guidelines sections. Every sentence adds a distinct fact, with no repetition of schema defaults or filler content.

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 moderate-complexity calculator with all parameters documented and no annotations or output schema, the description covers the key decision factors: when to use it, when not to use it, the formula, the alert threshold, side-effect profile, and the alternative tool. The lack of an exact output object is minor given how much contextual information is present.

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?

All four parameters already have 100% schema description coverage, which sets a baseline of 3. The description adds meaning beyond the schema by defining the central formula (Gross = Net / (1 - WHT_rate)) and explaining how statutory vs. treaty rates and the 183-day threshold relate to one another.

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 ('Calculate') and names precise resources: cross-border B2B consulting/software invoice tax gross-up, statutory vs. DTAA treaty withholding rates, and Permanent Establishment audit exposure. This clearly differentiates it from the many unrelated sibling calculators, and the usage section further distinguishes it from feie_nomad_tracker.

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?

States explicit 'Use when...' conditions for cross-border service exports and international client contract structuring. It also gives a direct exclusion ('Do not use for digital nomad individual income tax exclusion') and names the concrete alternative tool, feie_nomad_tracker.

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 of behavioral disclosure. It fully satisfies this by stating the calculation is deterministic and idempotent with zero external side effects, listing the exact governing equations, describing unit conversions, and specifying output units for deflection, moment, and stress.

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 structured in three compact sections: purpose, behavior, and usage guidance. Every sentence carries useful information, with the core purpose front-loaded and no filler or redundant restatement of the tool name.

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 calculation tool with five parameters, no annotations, and no output schema, the description provides everything an agent needs: formulas, unit handling, return units, use cases, and explicit exclusions. There are no significant gaps that would prevent correct selection or 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?

Since schema description coverage is 100%, the schema already documents each parameter's units and positivity constraints. The description adds value beyond this by mapping parameters to the formulas (P, L, E, I, y) and clarifying unit conversions, though it does not independently explain every parameter's contribution.

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 a specific verb ('Calculate structural engineering beam mechanics') and names the exact outputs: maximum elastic deflection, peak bending moment, and maximum flexural stress. It also states the load case and beam model (center point load, simply supported Euler-Bernoulli beam), making its purpose unmistakable and distinct from sibling tools.

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 says when to use the tool ('civil, structural, and mechanical engineering beam sizing and load checks') and when not to use it ('Do not use for fluid pipe friction or pressure drop'), naming the alternative tool pipe_flow. This gives an agent clear routing guidance with no inference required.

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 present, so the description carries the full burden. It explicitly states 'Deterininistic, idempotent calculation with zero external side effects' and spells out the underlying equation (Gross - Expenses - Health - SECA Tax - Income Tax = Target Net Cash) and how billable hours are derived. This goes well beyond the schema by disclosing exactly what happens when invoked.

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 descriotion is organized into three clear sections: purpose, behavior, and usage guidelines. It is front-loaded with the main goal, and every sentence adds necessary context—no filler. It is concisely sized for a multi-parameter financial calculator.

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 having no output schema, the description makes the return value clear (the hourly billable floor) and explains the calculation logic and inputs thoroughly. It also gives explicit context on when to select this tool over contractor_parity. An agent has enough information to invoke it correctly and interpret the result.

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 descriotion coverage is 100%, so baseline is 3. The descriotion adds value by mapping domain concepts ('vacation weeks', 'non-billable admin/marketing percentage', 'deductible overhead') to parameters and showing how they affect the calculation, but it doesn't add per-parameter details beyond the schema. This modest extra semantic linking warants a 4.

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 a specific verb 'Solve' and a precise output object: the exact minimum billable hourly rate needed to hit a target net spendable cash income. It enumerates the key factors (unpaid weeks, admin drag, deductible overhead, health insurance, SECA) and later differentiates itself from contractor_parity in usage guidelines, so it is immediately distinguishable from siblings.

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 an explicit when-to-use: freelancer, consultant, or agency owner setting a baseline hourly rate to support a lifestyle budget. It also provides a clear when-not-to-use: benchmarking against a specific W-2 salary offer, and routes to contractor_parity. This is exactly the desired when/when-not/alternative 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?

With no annotations provided, the description carries the full burden and states 'Deterministic, idempotent calculation with zero external side effects' – a clear behavioral disclosure. It also reveals internal computation (d1/d2 formulas, polynomial approximations) and the exact outputs, including put-call parity and Greeks, which goes far beyond a bare 'computes options' statement.

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?

Despite covering purpose, formulas, behavior, and usage, the description is organized into labeled sections and stays compact. Every sentence contributes either scope, behavioral transparency, or alternative routing; there is no filler or 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?

The tool has no output schema, so the description appropriately enumerates return values: call/put prices, put-call parity check, and all major Greeks. It also covers scope (European options), behavioral safety (pure function), and usage context. Nothing critical is missing for an agent to invoke it 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 input schema has 100% description coverage, so the baseline is 3; each parameter already carries units, defaults, and constraints. The description reinforces the mapping to Black-Scholes variables (S, K, r, sigma, T) but does not add meaning beyond the schema. Thus no extra compensation is required.

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 a specific verb ('Compute') and a precise domain: European option pricing via the Black-Scholes-Merton model, listing Call/Put values and the standard Greeks. This clearly differentiates it from siblings like npv_irr and project-planning tools. The resource and scope are 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?

There is an explicit 'Usage Guidelines' section: use for financial derivatives pricing, risk management, and hedging; do not use for capital budgeting or cash flow discounting, with npv_irr named as the alternative. This directly tells an agent when to select this tool versus a sibling.

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 and does so thoroughly: it declares the operation deterministic, idempotent, and side-effect-free, and gives exact equations for each derived value. It also notes the return behavior ('Returns detailed breakdown'), so an agent knows what to expect.

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 organized into a terse summary, a behavior block, and a usage block with no wasted sentences. The core outputs are front-loaded, and formula details are compactly formatted.

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 a fully documented schema, no output schema, and no annotations, the description provides enough computational detail, optional-input behavior, and routing guidance for an agent to invoke the tool correctly. The formulas plus 'Returns detailed breakdown' are sufficient to predict the output.

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 baseline is 3; the description adds value by showing how parameters map into formulas (unitPrice - unitVariableCost, fixedCosts / CM) and by explaining the conditional role of expectedUnitsSold. This goes beyond the schema's field-level descriptions without needing to restate them.

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 a specific verb and resource: 'Calculate cost-volume-profit break-even thresholds...' and enumerates outputs (units, revenue, CM ratio, margin of safety, DOL). It further differentiates itself from billable_floor by explicitly naming the alternative.

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 concrete use cases ('pricing strategy, manufacturing and SaaS unit economics, operational risk appraisal') and an explicit negative case with the correct alternative ('Do not use for hourly freelance billing rate minimums; use billable_floor instead').

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 of behavioral disclosure. It states 'Deterministic, idempotent calculation with zero external side effects,' provides the exact formulas used, and enumerates all return values: nominal CAGR %, real CAGR %, total nominal gain, total real purchasing power gain, and doubling years.

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 well-organized with clear sections for behavior and usage guidelines. Every sentence adds information: formulas clarify behavior, return-value enumeration aids expectations, and the sibling comparison prevents misuse. It is detailed without being bloated.

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 having no output schema, the description fully enumerates what the tool returns. It also covers the main use cases and explicitly routes the agent away from inappropriate sibling tools. Combined with 100% schema parameter coverage, the description leaves no critical gap for correct selection and 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?

Schema description coverage is 100%, so the baseline is 3. The description adds value by showing exactly how parameters are used in formulas, e.g., 'finalValue / initialValue' and 'periodsYears' as the exponent, and 'Inflation' in the Fisher relation. This goes slightly beyond the schema by tying parameters to their computational roles.

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 and resource: 'Calculate Compound Annual Growth Rate (CAGR), real inflation-adjusted purchasing power growth (Fisher equation), and exact investment doubling time.' This clearly names the calculation types and distinguishes the tool from siblings like compound_wealth and sip_investment by 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?

Explicit usage guidance is given: 'Use for evaluating historical investment portfolio track records, business revenue growth metrics, and inflation drag analysis.' It also names the exact alternatives to avoid: 'Do not use for forward-looking recurring monthly investment projections; use compound_wealth or sip_investment instead.'

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 full responsibility for behavioral disclosure. It discloses determinism, idempotence, zero external side effects, the mathematical methods used (discriminant, Cramer's rule), complex-conjugate root behavior, vertex calculation, and singular/parallel system detection. The only minor gap is an explicit error-handling contract for invalid inputs beyond the schema's non-zero requirement for 'a'.

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 organized into clear sections with each sentence carrying distinct information: scope, behavioral guarantees, mathematical details, and usage boundaries. There is no filler or 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?

For a mathematical solver with no output schema and no annotations, the description covers all operation modes, the formulas used, expected outcomes (real/complex roots, vertex coordinates, singular systems), and usage guidance. It does not enumerate the exact response JSON structure, but the computed quantities are sufficiently specified for an agent to infer the output shape.

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 baseline is 3. The description adds real value by explaining how the same coefficients map to different meanings depending on mode, and by showing the mathematical formulas (e.g., discriminant, Cramer's rule) that define the parameter semantics beyond the schema's per-field 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 states a specific verb ('Solve') and resource ('algebraic polynomial equations'), and enumerates exactly the two supported equation types with explicit formulas. It distinguishes itself from siblings by naming linear_regression as the alternative for statistical fitting.

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 inclusion criteria ('Use when solving quadratic polynomials or 2-unknown linear systems') and exclusion criteria ('Do not use for statistical data fitting; use linear_regression instead'). This leaves no ambiguity about when to select this tool versus a sibling.

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 behavioral burden and does so well. It discloses that the tool is deterministic, idempotent, has zero external side effects, details the exact pricing tier structure, and specifies what outputs are returned. This gives the agent strong expectations for invocation and result interpretation.

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 well-structured with clear Behavior and Usage Guidelines sections. The core purpose is front-loaded, and each sentence adds information—pricing rates, computational behavior, outputs, and usage boundaries—without fluff 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?

For a two-parameter calculator with no output schema, the description sufficiently explains inputs, calculation logic, pricing tiers, and return values. It also provides usage boundaries and a sibling alternative, making the tool self-contained for 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?

Schema description coverage is 100%, and both parameters have detailed descriptions with defaults and examples. The tool description adds conceptual context around cache offload and cost savings but does not meaningfully enhance per-parameter semantics beyond 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 states the tool analyzes AWS/GCP tiered egress pricing versus Cloudflare zero-egress options and quantifies cost savings. It uses a specific verb ('Analyze') and distinct resource domain, differentiating it from the sibling ai_token_arbitrage and other calculators.

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 Usage Guidelines section explicitly states when to use the tool ('cloud architecture budgeting, FinOps reviews, evaluating CDN caching or Cloudflare migration economics') and when not to use it ('Do not use for LLM token pricing'), naming the alternative tool. This gives an agent clear decision 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?

No annotations are provided, so the description carries the full burden. It discloses that the calculation is deterministic, idempotent, and has zero external side effects, gives the exact discrete compound interest formula with periodic annuity deposits, and enumerates what it returns. This goes well beyond typical tool descriptions and gives the agent a clear behavioral model.

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?

Three tight paragraphs: purpose, behavior/formula/outputs, and usage guidance. The most decision-relevant information is front-loaded, and every sentence contributes meaning. No filler or 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?

Despite having no output schema and no annotations, the description is self-sufficient: it explains the calculation domain, formula, side effects, return values, and routing to an alternative tool. Nothing essential for an agent to select and invoke this tool correctly 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 the baseline is 3. The description adds value by explaining the formula with variables (P, r, n, t, PMT), clarifying that monthly deposits are periodic annuity contributions, and describing the outputs. It does not restate each parameter but complements the schema with calculation 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?

States a specific verb ('Simulate') and resource ('long-term compound interest growth'), names relevant use cases (retirement portfolios, 401(k)s, Roth IRAs, UK ISAs, European ETF savings plans), and distinguishes itself from sip_investment by explicitly excluding Indian mutual fund SIPs with annual step-up. An agent can immediately understand what this tool does and how it differs from an important sibling.

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 guidance: use for multi-year personal wealth projection and retirement nest-egg simulations, and explicitly says not to use it for Indian mutual fund monthly SIPs with annual step-up, directing the agent to sip_investment instead. This is clear when-to-use and when-not-to-use guidance with a named alternative.

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 and meets it: 'Deterministic, idempotent calculation with zero external side effects' discloses the side-effect profile. It further lists the tax components computed (FICA, SECA, QBI, etc.) and specifies the returned artifacts: net spendable cash, tax breakdowns, effective rates, and exact breakeven rate.

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 text is organized into labeled purpose, behavior, and usage blocks. Every sentence carries information: main calculation, side-effect profile, computation list, return list, use case, and exclusion with alternative. There is no filler or repetition of schema content.

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 complex 13-parameter calculator with no output schema, it covers purpose, usage boundaries, computation scope, outputs, and side effects. It stops short of stating tax-year/statutory-rate assumptions or explicitly describing how selectedRail and targetCurrency affect the net conversion, so it is not quite exhaustive.

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 summarizes related parameters conceptually (401(k) match, health subsidy, PTO value, QBI) but does not add per-parameter details beyond what the schema's own descriptions already provide.

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?

Opens with a specific verb-resource pair: 'Calculate tax liabilities, statutory benefits, and net take-home cash between W-2 salaried employment and 1099 independent contractor billing.' It also names the exact deliverable, 'breakeven billing rate ($/hr)', making the tool's scope unambiguous and distinguishable from siblings like billable_floor.

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 the trigger: 'Use when an individual or hiring manager is deciding between a W-2 salaried offer and a 1099 contractor contract.' It also gives a when-not-to and an alternative: 'Do not use for solo freelancer baseline rate setting without a W-2 benchmark; use billable_floor instead.' This is ideal routing 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?

No annotations are provided, so the description carries the full burden. It explicitly discloses deterministic, idempotent, zero-side-effect behavior; describes the 330-day threshold check, statutory cap application, excess-income tax computation, and state domicile warnings. The only notable omission is the exact return value structure, but core behavioral transparency is 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?

The description is organized into purpose, behavior, and usage sections, with each sentence carrying meaningful information. It is slightly redundant by repeating the $130,000 cap, but remains compact and front-loaded with the most important purpose information.

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 output schema and no annotations, the description must supply substantial context, and it largely does: use case, algorithm, parameter relevance, and sibling differentiation. The main gap is not describing the exact result format, such as whether it returns a boolean, a tax amount, or warnings, but this is inferable from the stated behavior.

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 baseline is 3. The description adds meaning by connecting daysOutsideUSInRollingPeriod to the 330-day requirement, mentioning statutory limits across tax years, and naming high-audit states beyond the schema's examples. This provides useful context beyond parameter names and defaults.

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 a specific verb 'Track' and names the exact resource: IRS Form 2555 Foreign Earned Income Exclusion, Physical Presence Test, 330-day threshold, statutory cap, and sticky domicile risks. This clearly distinguishes the tool from generic tax calculators and from the sibling b2b_withholding_risk.

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?

Contains explicit 'Use for' and 'Do not use for' guidance, naming the alternative tool b2b_withholding_risk for foreign corporate withholding tax. This gives an agent clear selection criteria and prevents misuse.

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 behavioral disclosure burden. It clearly states the calculation is deterministic, idempotent, and has zero external side effects, and it details what is modeled: fixed wire fees, percentage platform fees, and hidden FX spreads. It also enumerates the output table fields, giving the agent a clear model of what happens when it calls the 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 organized into three tight sections: purpose, behavior, and usage guidelines. Every sentence earns its place, there is no redundant filler, and the most important scoping information is front-loaded in the first sentence.

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 deterministic calculation tool with two well-documented parameters and no output schema, the description is complete: it covers the calculation scope, fee models, output contents, and when to use or avoid the tool. The absence of an output schema is mitigated by explicitly listing the returned ranked table fields.

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 both parameters already have clear descriptions in the schema: invoiceUsd is the gross billed invoice amount in USD, and targetCurrency is the payout destination currency code. The description adds useful context about fee components and return values, but it does not need to compensate for missing parameter documentation, so baseline 3 applies.

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 specific verbs ('Quantify', 'calculate') and names a precise resource: cross-border payment fee drag and net landed local currency across 6 named payout rails. It also clearly distinguishes itself from the sibling contractor_parity by naming the non-use case.

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?

Usage guidelines explicitly state when to use the tool: when an international freelancer, remote worker, or cross-border vendor needs the cheapest payout rail or invoice amount in USD. It also gives an explicit exclusion and names the alternative tool, contractor_parity, leaving no ambiguity.

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 of behavioral disclosure. It clearly states the calculation is deterministic, idempotent, and has zero external side effects, provides the exact formula and interest-rate conversion, and enumerates the return values including first-year amortization breakdown.

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 well-structured and front-loaded: purpose first, then behavior/formula, then usage guidelines. Every sentence contributes distinct value, and there is no redundant 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?

For a calculation tool with no output schema and no annotations, the description is remarkably complete: it explains what is computed, how it is computed, what is returned, and when to avoid it. The only missing item would be an example, but that is not necessary for 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?

Schema description coverage is 100%, so the schema already documents all parameters. The description adds meaningful mathematical context by mapping principal, interestRatePercent, and tenureYears to the formula variables (P, r, n) and explaining the annual-rate-to-monthly-rate conversion, which goes beyond the schema's basic field definitions.

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 ('Calculate') with a precise resource ('reducing-balance monthly EMI'), and specifies outputs (total interest, amortization schedule) and loan scope (home, auto, personal). It also distinguishes itself from mortgage_piti, so an agent can differentiate it from siblings.

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 when to use the tool ('general global reducing-balance loans and consumer debt') and when not to use it ('US residential mortgages requiring property tax, hazard insurance, and PMI escrow'), naming the alternative tool (mortgage_piti). This is clear, actionable routing 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?

No annotations are provided, so the description carries the full burden and fully meets it. It discloses that the tool is 'Deterministic, idempotent calculation with zero external side effects', then specifies slab rates, Section 87A rebate, cess, and the side-by-side comparison output.

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 well structured and front-loaded: the core purpose appears first, followed by a Behavior block with precise calculation rules, then Usage Guidelines. Every sentence carries substantive information with 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?

For a complex tax tool with no annotations and no output schema, the description is notably complete. It specifies the applicable financial year, slabs, rebate threshold, cess, target users, exclusions, and the return behavior of comparing regimes with an optimal recommendation.

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 because both ctc and isSalaried are already well documented in the schema. The description adds useful context about standard deduction and salaried eligibility, but it does not materially expand parameter-level meaning 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 opens with a specific verb and resource: 'Compute Indian personal income tax liability comparing the Union Budget 2025-26 New Tax Regime ... against the Old Tax Regime.' It clearly distinguishes itself from sibling tools by naming exact alternatives for US taxes and by scoping itself to Indian personal income tax.

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?

Usage guidance is explicit and actionable: 'Use when computing personal income tax or payroll deductions for Indian residents and salaried professionals.' It also provides a clear exclusion and alternative routing: 'Do not use for US federal/state taxes; use contractor_parity or solo_401k_shield instead.'

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 present, the description carries the full behavioral burden and succeeds: it states 'Deterministic, idempotent calculation with zero external side effects' and reveals the computational method (covariance/variance formulas, intercept calculation, standard error, predicted values). No annotation contradiction exists because annotations are absent.

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 main purpose and outputs, then separated into Behavior and Usage Guidelines. Each sentence adds value and the structure makes scanning easy for an agent.

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 one-parameter calculator with no output schema, the description names all computed outputs (line equation, r, R^2, standard error, predicted y-values), details the calculation, and states the accepted input shape in the schema. Nothing an agent needs to select or call it correctly 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?

The input schema has 100% coverage, so the baseline is 3. The description reuses the same x/y independent/dependent variable concepts already present in the schema and does not add meaningfully new parameter information beyond the formula context.

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 a specific verb and resource: 'Compute Ordinary Least Squares (OLS) bivariate linear regression best-fit trend line...' plus Pearson r and R^2. It clearly distinguishes the tool from siblings, particularly casio_991_solve, by stating it computes a best-fit trend rather than solving systems.

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 Usage Guidelines say when to use it ('trend forecasting, scientific scatter data fitting, correlation analysis') and when not to ('Do not use for solving analytical quadratic or linear systems'), naming the alternative casio_991_solve. This gives an agent a clear routing decision.

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 behavioral burden and does so well: it discloses determinism/idempotence, zero external side effects, the fixed-rate annuity formula, tax/insurance monthly divisor, conditional PMI with 78% LTV threshold, and the output components. No annotation 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 front-loaded with the core purpose and then uses compact labeled paragraphs for behavior and usage. Every sentence contributes either scope, formula behavior, output information, or routing guidance, with 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?

For an 8-parameter tool with no annotations and no output schema, the description is remarkably complete: it covers formula, edge-triggering behavior, output summary, target use cases, and the exact alternative. The only minor caveat is the '30-year' default framing, but the schema's tenureYears/loanTermYears descriptions clarify the variable term.

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 baseline is 3. The description adds extra semantics for how parameters interact, notably that down payments under 20% trigger PMI until 78% LTV and that property tax and insurance are converted to monthly amounts, which goes beyond the individual parameter 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?

States a precise verb ('Calculate') and resource ('monthly US mortgage payments broken down into PITI...along with full 30-year amortization schedule'). The US/PITI framing differentiates it from international loan calculators like home_loan_emi, and the first sentence alone tells an agent what the tool produces.

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 specifies when to use the tool ('US residential home purchase financing and refinancing scenarios') and when not to ('Do not use for international reducing-balance loans without escrow/PMI'), naming the alternative tool (home_loan_emi). This is model routing 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?

With no annotations, the description carries the full transparency burden and meets it: deterministic, idempotent, no external side effects, exact formula, iteration count/tolerance, and the returned values. It discloses the algorithm's behavior beyond what any schema could infer.

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?

Three targeted paragraphs front-load the action and scope, then behavior, then usage. Every sentence adds a distinct fact; no filler or repeated schema content.

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?

Although there is no output schema, the description declares the full return set (NPV, IRR percentage, PI, payback period). Combined with 100% schema parameter coverage and explicit algorithm limits, an agent has enough to invoke it correctly and interpret the result.

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 formula NPV = -C0 + sum(Ct/(1+r)^t) adds conceptual context, but the description does not add parameter-level detail beyond the schema's clear definitions for cashflows, initialInvestment, and discountRatePercent.

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 a specific verb and resource set: compute NPV, IRR via Newton-Raphson, and discounted payback period. It clearly separates this capital-budgeting tool from financial siblings by naming compound_wealth as the alternative for fixed-deposit growth.

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 appropriate use cases (capital investments, M&A valuations, corporate projects, multi-year hurdle rates) and an explicit exclusion ('Do not use for simple compound interest projections with fixed monthly deposits'), directing the agent to compound_wealth. This is model 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?

With no annotations, the description carries the full behavioral burden and does so well: it states determinism, idempotence, zero side effects, key equations, flow-regime thresholds, and return units. It loses a point by not clarifying behavior for the transition region Re = 2000–4000, which is left ambiguous.

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 well-structured with a brief purpose sentence, a behavior section, and a usage section. Every sentence adds information; there is no filler or 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?

For a tool with no output schema, the description provides strong context: outputs, units, equations, and regimes. However, it does not explicitly state that the friction factor is also a return value, and it omits transition-region handling, which an agent might need to interpret results 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?

Input schema coverage is 100%, so the baseline is 3. The description adds meaningful semantic value beyond the schema by showing how parameters relate through equations (v = Q/A, Re = rho*v*D/mu) and by defining laminar and turbulent friction factor behavior.

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 a specific verb and resource: calculating Darcy-Weisbach friction factor, Reynolds number, head loss, and pressure drop for closed circular pipes. It clearly defines scope and distinguishes itself from siblings like beam_bending through explicit wording.

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 Usage Guidelines explicitly list appropriate use cases (hydraulic design, water supply, chemical lines, HVAC) and give a concrete exclusion with an alternative tool ('Do not use for structural beam stress; use beam_bending instead'). This gives an agent clear routing 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?

With no annotations provided, the description fully carries the behavioral burden. It discloses determinism, idempotence, zero side effects, the vacuum/constant-gravity assumption, the governing equations, and the returned components. This is rich, accurate behavioral context beyond what structured data could provide.

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?

Every sentence earns its place: purpose, behavior, equations, return values, and usage boundaries are all covered without repetition. The content is front-loaded with the core calculation summary before the detailed behavior and usage.

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 deterministic calculation tool with no output schema and no annotations, the description is sufficiently complete. It explains assumptions, formulas, return values, and usage boundaries, so an agent has everything needed to select and invoke it 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 schema already documents all three parameters clearly. The description references v0, theta, and g in formulas, but adds little beyond the schema. Per the rubric baseline, a 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 names a specific calculation domain (2D projectile kinematics), lists the exact outputs (apex height, range, flight time, impact velocity), and distinguishes itself from rocket_deltav. An agent can clearly identify what this tool computes and how it differs from sibling physics/finance calculators.

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 states when to use the tool ('ballistic trajectories, physics problem solving, aerospace launch kinematics without atmospheric drag') and when not to use it ('Do not use for orbital delta-v rocket staging; use rocket_deltav instead'). This gives unambiguous routing 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?

With no annotations provided, the description carries the full burden and delivers: it states 'Deterministic, idempotent calculation with zero external side effects' and then discloses the exact formulas used. This makes the tool's behavior and non-mutating nature fully 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 well-structured: a front-loaded summary, a separate Behavior section with formulas, and a Usage Guidelines section. There is no filler, and the formula details earn their place because they define the tool's computation precisely.

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 without an output schema, the description explicitly names all computed quantities and the condition under which the optional frequency-dependent calculations occur. An agent has enough information to invoke the tool correctly and understand the results.

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 already provides 100% coverage with units and positivity constraints for every parameter. The description goes further by embedding each parameter into the relevant physical equations, clarifying how resistance, inductance, capacitance, and frequency are used 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 a specific verb and resource: 'Calculate AC electrical resonance properties for series RLC circuits' and enumerates exact outputs (f0, Q, bandwidth, impedance magnitude). The domain is so specific that it is clearly distinguishable from all sibling tools, most of which concern finance, mechanics, or unrelated physics.

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 explicit positive use cases ('RF tuning, audio filter design, and electrical circuit frequency response analysis') and explicit negative exclusions ('Do not use for power grid transmission lines or mechanical vibrations'). This gives an agent practical routing guidance without needing to inspect 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?

With no annotations present, the description carries the full burden of behavioral disclosure. It clearly states the operation is 'deterministic, idempotent calculation with zero external side effects,' reveals the exact equation evaluated, and lists the derived quantities and return units. It stops short of describing edge-case behavior or exact response structure, hence not a 5.

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 well-structured with labeled sections (Behavior, Usage Guidelines) and contains no filler. The opening sentence slightly overlaps with the formula restatement in Behavior, but each sentence contributes substantive detail, so the length is justified.

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 tool has no output schema and no annotations, so the description must compensate; it does by covering the formula, outputs in m/s and km/s, use cases, and exclusions. However, it does not specify the full return payload shape or explicitly confirm that mass ratio and propellant consumption are included in the return value, leaving minor ambiguity.

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 baseline is 3, but the description adds value by mapping parameters to the equation variables (m0, mf, Isp, g0) and showing how they interact in the Tsiolkovsky equation. This goes beyond the individual parameter descriptions and helps an agent reason about 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 a specific verb ('Calculate') tied to a precise resource: 'aerospace orbital mechanics delta-v budget, mass ratio, and propellant consumption using the Tsiolkovsky rocket equation.' It names the sibling tool it is not (projectile_motion), making the tool immediately distinguishable from other physics/engineering calculators.

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?

Usage Guidelines explicitly state when to use this tool ('rocket stage sizing, orbital insertion maneuver budgets, mission delta-v planning') and when not to ('Do not use for ballistic atmospheric projectile flight'), and they name the alternative: 'use projectile_motion instead.' This is exactly the kind of decision support an agent needs.

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 caries full responsibility for behavioral disclosure. It does this thoroughly: deterministic, idempotent, zero external side effects, wages vs. distributions, 15.3% FICA on salary only, employer-half deduction, fee deductions, and breakeven threshold calculation.

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 organized into purpose, behavior, and usage guidelines with no filler. Each sentence adds necessary information and the structure aids quickscanning for an agent.

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 absence of an output schema, the description still specifies the core output via 'net tax savings' and 'breakeven net profit threshold,' and covers input behavior, usage context, and exclusions. An agent has enough 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?

Schema description coverage is 100%, so the baseline is 3. The description adds value by explaining how salaryPercent relates to netProfit and how CPA/payroll fees enter the calculation, plus the IRS reasonableness context for salaryPercent.

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 a specific verb and resource: 'Evaluate S-Corporation tax election viability' and enumerates the concrete calculatons (salary split, payroll tax shield, overhead costs, net tax savings) under a cited IRS ruling. This makes the tool's purpose unmistakable and distinguishes it from sibling calculators like solo_401k_shield.

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?

Usage Guidelines explicitly states when to use (US small business owner, single-member LLC, freelancer considering S-Corp status) and when not to use, directing the agent to solo_401k_shield for retirement contribution limits. This provides clear selection criteria and an alternative.

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 fully carries the burden of behavioral disclosure. It states the calculation is deterministic, idempotent, and has zero external side effects, explains the compounding formula, describes how step-up increases installments every 12-month cycle, and lists the return values (maturity amount, total invested capital, total capital gains, year-by-year accumulation).

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 well-structured with a clear opening sentence, a focused behavior section, and a usage section. Every sentence earns its place, and the most important scoping information is front-loaded before the alternative tool is named.

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 financial complexity, lack of annotations, and absence of output schema, the description is remarkably complete. It covers the formula, the semantic behavior of step-up, the returned data, and when to choose a different tool, giving an agent everything needed to invoke it 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 adds meaningful parameter context beyond the schema by explaining the step-up mechanism ('dynamically increases monthly installment each 12-month cycle') and clarifying that monthlyInvestment is the initial installment, which strengthens understanding of how stepUpPercent modifies it over time.

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 ('Calculate') with a clear resource ('Systematic Investment Plan mutual fund maturity wealth') and an optional qualifier ('annual percentage step-up'). It clearly distinguishes itself from the sibling compound_wealth by explicitly naming it as the alternative for different use cases.

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 the tool ('mutual fund SIP investments, recurring deposits, and goal-based financial planning') and when not to use it ('US 401(k) / Roth IRA compounding with lump sum'). It also names the exact alternative tool, compound_wealth, leaving no ambiguity for the agent.

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 present, the description fully carries the behavioral burden. It discloses determinism, idempotency, zero side effects, the exact contribution formulas for entityType, age-based catch-up thresholds, statutory caps, and how the final cash savings number is computed. This is unusually 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 organized into a focused opening sentence, a Behavior breakdown, and Usage Guidelines. Every sentence adds a distinct piece of decision-relevant information, with no repetition or filler. The structure makes the content easy to scan.

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 tool is fully documented on inputs, formulas, and high-level return value ('returns net cash saved'), and the absence of an output schema is partially compensated. However, there is mild ambiguity about whether the output includes both the Solo 401(k) vs SEP-IRA comparison and the cash savings figure, or only a single net result. A brief statement of the output shape would make it fully self-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?

Even though schema coverage is 100%, the description adds meaningful formula-level semantics: 20% of adjusted net earnings for LLC/sole prop vs 25% of W-2 salary for S-Corp, age 50+ catch-up limits, and marginal tax rate multiplication. This helps an agent map each parameter to real-world inputs beyond the bare 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 begins with a precise verb and object: maximizing tax-deferred retirement sheltering by comparing Solo 401(k) and SEP-IRA limits and calculating cash tax savings. It is unambiguous about the domain and statutory caps, and the Behavior section further distinguishes it from investment-growth tools like compound_wealth.

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?

Usage Guidelines explicitly state when to use the tool ('owner-only business, independent contractor, or partner wants to optimize pre-tax retirement deductions') and when not to use it, naming the sibling alternative compound_wealth instead. This is exactly the kind of clear routing guidance an agent needs.

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 full responsibility for behavioral disclosure. It clearly states the calculation is deterministic, idempotent, and has zero external side effects, then reveals the core formulas: net burn, runway months, SAFE equity percentage, Series A option pool expansion, and founder ownership calculation.

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 well organized into purpose, behavior, and usage sections. Every sentence provides useful information: formulas, side-effect guarantees, use cases, and exclusions. Despite covering a complex multi-step model, it remains focused and free of 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 tool has 8 parameters, no output schema, and no annotations, the description is unusually complete. It names all computed outputs, explains the calculation logic, lists appropriate use cases, and provides an explicit alternative for out-of-scope scenarios. An agent has enough context to invoke it correctly and interpret its results.

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 baseline is 3, but the description adds substantial semantic value by explaining how the parameters interrelate: monthlyGrossBurn and monthlyRevenue form net burn, cashOnHand drives runway months, safeInvestment and postMoneyCap determine SAFE dilution, and seriesAPreMoney, seriesAInvestment, and optionPoolExpansionPercent drive the Series A waterfall. This goes well beyond the schema's individual parameter 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 opens with a specific verb 'Model' and names three concrete resources: cash runway exhaustion, SAFE conversion cap dilution, and Series A option pool waterfall. This clearly distinguishes it from sibling financial tools like npv_irr and black_scholes.

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 states applicable use cases ('venture capital fundraising planning, startup cash runway tracking, and cap table dilution modeling') and explicitly excludes DCF/IRR appraisal, directing the agent to npv_irr instead. This is exactly the kind of when-to-use and when-not-to-use guidance needed.

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 behavioral disclosure burden. It explicitly states 'Deterministic, idempotent calculation with zero external side effects' and describes the calculation steps including 'fair penny rounding.' The only notable gap is that the return format or error handling is not stated, but for a simple calculator this is adequate.

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 well-organized with a front-loaded purpose, a behavior section, and a usage section. It is efficient and every paragraph earns its place. There is slight redundancy between the opening sentence and the behavior paragraph, but no filler or irrelevant detail.

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 simple calculator with all parameters documented in the schema, the description is nearly complete: it covers use cases, exclusions, computation behavior, and side-effect profile. The only missing piece is an explicit statement of the return object shape, which would be more critical since no output schema is provided.

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 earns an extra point by explaining how billAmount, tipPercent, and numPeople are used in the calculation ('Multiplies pre-tip subtotal by tip percentage... divides by party size') and by adding 'fair penny rounding' semantics that are not present in 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 opens with a specific verb and resource: 'Compute restaurant bill gratuity, total payable bill, and fair per-person itemized payment split.' This immediately tells an agent what the tool produces and distinguishes it from generic payment or tax tools. It also names vat_sales_tax as a sibling alternative, further clarifying 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?

Provides explicit 'Use for' scenarios (restaurant dining bills, food delivery tips, group expense splitting) and an explicit 'Do not use for' exclusion (commercial corporate tax or VAT) with a named alternative, vat_sales_tax. This gives an agent clear routing guidance without needing to infer.

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 and does well: it discloses deterministic, idempotent behavior, zero external side effects, exact formulas, and 2-decimal rounding. It loses one point because 'statutory rate verification' is mentioned but never explained, and error/invalid-input behavior is not covered.

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 well-organized into purpose, behavior, and usage sections, with no redundant sentences. The phrase 'with statutory rate verification' is somewhat vague but does not bloat the description significantly.

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?

Although there is no output schema, the description states what is returned: 'net, tax amount, and gross values rounded to 2 decimal places.' It also covers modes and formulas. It is not a 5 because it does not address validation failures or clarify the statutory rate verification claim.

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 baseline is 3. The description adds value by spelling out the formulas tying amount and vatRatePercent together, and clarifying which amount is net vs gross in each mode. This goes beyond the schema's per-property 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 states a specific verb and resource: 'Calculate European Value Added Tax (VAT) and global sales taxes' with Add and Remove modes. It clearly distinguishes this from sibling financial/calculation tools by naming its tax domain and explicitly excluding restaurant tipping in favor of tip_splitter.

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 use cases: 'e-commerce, international invoicing, retail pricing, and VAT compliance calculations.' It also provides a direct exclusion and alternative: 'Do not use for restaurant tipping and bill splits; use tip_splitter instead.'

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