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 effectively describes the tool's behavior: it performs a mathematical conversion (not destructive), handles input validation (beta must be 0-1), returns a dictionary with specific fields, and notes accuracy limitations (approximate, depends on distribution). However, it lacks details on error handling or performance aspects like rate limits, leaving minor gaps.

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 sections (e.g., Parameters, Use Cases, Returns), but it is verbose with extensive background information (e.g., definitions of beta and Lorenz coefficients, typical ranges) that, while informative, could be condensed. Some sentences, like detailed explanations of beta and Lorenz, may not be essential for tool invocation, reducing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (mathematical conversion with accuracy caveats), no annotations, and an output schema (implied by the Returns section), the description is highly complete. It covers purpose, usage, parameters, returns, common mistakes, example usage, and notes on assumptions, providing all necessary context for an AI agent to use the tool correctly without relying on structured 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?

The schema description coverage is 0%, so the description must fully compensate. It provides extensive parameter semantics: defines 'value' as the Dykstra-Parsons beta coefficient (0-1), explains its calculation (β = (k50 - k84.1) / k50), gives typical ranges (0.3-0.8), and includes an example (0.6). This adds significant meaning beyond the bare schema, fully documenting the single 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 clearly states the tool's purpose: 'Convert Dykstra-Parsons beta to Lorenz coefficient.' It specifies the exact conversion (beta→Lorenz), distinguishes it from its sibling 'lorenz_to_beta' (reverse conversion), and provides context about heterogeneity metrics, making the purpose specific and differentiated.

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 outlines when to use this tool in the 'Use Cases' section, including literature conversion, reservoir comparison, simulation input, analog studies, and historical data conversion. It also distinguishes it from alternatives by noting that conversion assumes log-normal permeability distribution and may be less accurate for non-log-normal cases, providing clear guidance on applicability.

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 effectively describes what the tool does (computes comprehensive brine properties), mentions it uses industry-standard correlations, and includes practical details like common mistakes (e.g., unit conversions, temperature types) and effects of dissolved gases. However, it lacks explicit information on rate limits, error handling, or computational constraints, which slightly limits transparency.

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 sections like Parameters, Properties Calculated, Applications, and Returns, but it is overly verbose with redundant details (e.g., extensive lists of properties and applications). Some sentences could be condensed without losing clarity, making it less front-loaded and efficient than ideal for an AI 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 complexity of the tool (calculating multiple brine properties with gas saturation effects), no annotations, and an output schema that documents return values, the description is highly complete. It covers purpose, parameters, behavior, applications, common mistakes, and example usage, providing all necessary context for an agent to use the tool effectively without relying on structured 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 0%, so the description must fully compensate. It provides detailed parameter semantics beyond the schema, including units (psia, °F, wt%), valid ranges (e.g., p > 0, degf -460 to 1000, wt 0-30), typical values, examples, and explanations of effects (e.g., salinity increases density). This adds significant value over the minimal schema information.

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

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

The description explicitly states the tool calculates properties of CH4 or CO2 saturated brine, listing specific properties (density, viscosity, compressibility, formation volume factor) and distinguishing it from sibling tools like 'gas_density' or 'oil_density' by focusing on brine with dissolved gases. It uses clear verbs ('calculate', 'computes') and specifies the resource ('brine properties').

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 guidance on when to use this tool, listing applications such as aquifer analysis, water injection, CO2 sequestration, geothermal reservoirs, pressure maintenance, and material balance calculations. It also distinguishes usage from potential alternatives by specifying it's for brine (not gas or oil) and includes dissolved gas effects, with no misleading or contradictory information.

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 thoroughly explains the tool's behavior: it computes comprehensive properties, uses a specific model (Duan & Sun 2003), accounts for mutual solubility, handles unit systems, includes physics effects (pressure, temperature, salinity), and returns a detailed dictionary. It also notes critical applications and common pitfalls, providing rich behavioral context beyond basic functionality.

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 sections (Parameters, Properties Calculated, Applications, Returns, Common Mistakes), but it is lengthy with some redundancy (e.g., repeating mutual solubility details). Every sentence adds value, but it could be more front-loaded; the core purpose is stated early, but extensive details follow. It's efficient for a complex tool but slightly verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, no annotations, and an output schema (implied by 'Returns' section), the description is highly complete. It covers purpose, parameters, physics, applications, returns, common mistakes, and example usage. The output schema is described in detail in the 'Returns' section, making it fully adequate for an agent to understand and use the tool effectively in context.

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

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

Schema description coverage is 0%, so the description must fully compensate. It provides detailed parameter semantics: pres (pressure in psia/bar with typical ranges), temp (temperature in °F/°C with typical ranges), ppm (salinity in ppm with conversion examples), metric (unit system flag), and cw_sat (compressibility calculation flag). Each parameter includes units, constraints, examples, and practical guidance, adding significant meaning 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 explicitly states the tool calculates CO2-brine mutual solubilities and properties using the Duan & Sun (2003) model, specifying the verb 'calculate' and resource 'CO2-brine mutual solubilities and properties'. It distinguishes from siblings like 'calculate_brine_properties' by focusing specifically on CO2-brine systems with mutual solubility, making it highly specific and differentiated.

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 guidance on when to use this tool for CO2 sequestration, CO2-EOR, geothermal applications, aquifer storage, and material balance calculations. It includes a 'Common Mistakes' section with warnings about unit systems, salinity conversion, and compressibility flags, offering clear when-to-use and when-not-to-use advice without naming specific 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 provided, the description carries the full burden. It discloses that the tool 'computes' and 'returns' values, implying a read-only calculation, and mentions that 'evolved gas composition changes with pressure' which adds useful behavioral context. However, it lacks details on error handling, performance, or limitations.

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

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

The description is well-structured with a clear purpose statement, usage contexts, behavioral note, and return details. It is appropriately sized, though the bulleted list of applications could be slightly more concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a physics-based calculation with 1 parameter (a nested object) and an output schema, the description is reasonably complete. It explains the tool's purpose, usage, key behavioral aspect (pressure variation), and return format, though it could benefit from more detail on input constraints or examples.

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 schema description coverage is 0%, so the description must compensate. It adds significant meaning beyond the schema by explaining that parameters include 'oil properties, pressure(s), and separator conditions', clarifying the purpose of the nested 'request' object and its role 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 clearly states the specific action ('Calculate evolved gas specific gravity') and resource ('gas evolved from oil as pressure decreases below bubble point'), distinguishing it from siblings like 'gas_sg_from_composition' or 'weighted_average_gas_sg' by focusing on pressure-dependent evolution from oil.

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

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

The description provides clear context for when to use this tool ('for material balance calculations, surface facility design, gas sales forecasting' and 'when pressure decreases below bubble point'), but does not explicitly state when not to use it or name alternative tools among the siblings.

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 effectively describes what the tool does (e.g., scans files, extracts data, reports errors) and the output format. However, it lacks details on error handling, performance characteristics, or any limitations (e.g., file size constraints), which prevents a perfect score.

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 sections (e.g., 'What It Does', 'Applications', 'Workflow'), making it easy to scan. However, it includes some redundancy (e.g., repeating tool purpose in multiple sections) and could be more concise by trimming less critical details without losing clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the tool (simulation diagnostics), no annotations, and an output schema present, the description is mostly complete. It covers purpose, usage, applications, and output format. However, it lacks details on potential errors or edge cases, which would enhance completeness for such a specialized 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?

Schema description coverage is 0%, so the description must compensate. It mentions 'Path to PRT file and output options' in the Args section, which aligns with the 'filename' parameter in the schema. However, it does not detail the 'silent' parameter or provide additional semantic context beyond what is minimally implied, resulting in a baseline score.

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

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

The description clearly states the tool's purpose with specific verbs ('extract', 'parse', 'scans', 'identifies') and resources ('convergence problem cells', 'ECLIPSE/Intersect PRT files'). It distinguishes itself from sibling tools by focusing on simulation diagnostics and problem cell extraction, unlike the sibling tools which are primarily for fluid properties, calculations, and validation.

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 provides usage guidelines through sections like 'Applications' (e.g., 'Convergence Debugging', 'Model QC', 'Performance Tuning', 'Numerical Stability') and 'Workflow' (a 5-step process). It clearly indicates when to use this tool—for analyzing simulation output files to debug issues—without needing to specify alternatives, as sibling tools serve different purposes (e.g., fluid property calculations).

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

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

With no annotations provided, the description carries full burden and delivers comprehensive behavioral information. It explains what the tool creates (idealized flow distribution, Lorenz curve with 20 points), curve behavior for different L values, assumptions (log-normal permeability distribution), limitations (may be inaccurate for non-log-normal distributions), and detailed return structure. It also warns about common mistakes like invalid coefficient ranges.

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 sections (SYNTHETIC FLOW PROFILE, Parameters, Lorenz Curve Generation, etc.) and front-loads the core purpose. While comprehensive, some sections like 'Applications' with 6 bullet points could be more concise. However, every sentence adds value and there's no redundant 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?

Given the tool's complexity (generating mathematical curves with specific behavior), no annotations, and 0% schema coverage, the description provides exceptional completeness. It covers purpose, usage, parameters, behavior, applications, returns, common mistakes, examples, and limitations. The existence of an output schema means the description doesn't need to fully document return values, but it still provides a helpful summary of the return dictionary structure.

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?

With 0% schema description coverage (schema only has 'value' with type/number and min/max constraints), the description fully compensates by providing rich parameter semantics. It explains the parameter is a 'Target Lorenz coefficient (0-1)', provides typical range (0.2-0.7), gives an example (0.5), explains what different values represent (L=0 perfect conformance, L>0 flow imbalance), and shows example usage. This adds substantial meaning 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 clearly states the tool's purpose: 'Generate flow fractions from Lorenz coefficient' and 'Creates idealized flow distribution matching a specified Lorenz coefficient.' It distinguishes from sibling 'lorenz_from_flow_fractions' by specifying this tool generates synthetic data while that tool works with measured data. The verb 'generate' and resource 'flow fractions' are specific and well-defined.

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 guidance on when to use this tool versus alternatives. It states: 'For actual reservoirs, use `lorenz_from_flow_fractions` with measured production data' and explains this tool is for generating idealized curves. The 'Applications' section further clarifies appropriate use cases like reservoir simulation, waterflood prediction, and sensitivity analysis.

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 full burden and excels. It details behavioral traits: the formula used (Cg = (1/Z) × (∂Z/∂P) - (1/P)), how compressibility decreases with pressure, typical ranges (50-500 × 10⁻⁶ 1/psi), ideal gas behavior at low pressure, and the return format (dictionary with value, method, units, inputs).

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 sections (Parameters, Compressibility Behavior, Formula, Returns, Common Mistakes, Example Usage, Note) and front-loads the purpose. While comprehensive, it's appropriately sized for a complex tool, though slightly verbose; every sentence adds value, earning its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, no annotations, and an output schema (which the description aligns with by detailing returns), the description is highly complete. It covers purpose, usage, parameters, behavior, formula, returns, common mistakes, and examples, leaving no gaps for effective tool 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?

The schema has 0% description coverage, so the description fully compensates. It provides detailed semantics for all 7 parameters: purpose (e.g., 'Gas specific gravity'), valid ranges, typical values, examples, optional/default status, and for 'zmethod', it lists options and recommends 'DAK'. This adds substantial meaning 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 clearly states the tool calculates gas compressibility (Cg), specifying it's a critical PVT property that measures gas volume change with pressure. It distinguishes from sibling tools like 'oil_compressibility' by explicitly contrasting gas vs. oil compressibility ranges (100-1000 × 10⁻⁶ vs 5-50 × 10⁻⁶ 1/psi).

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 guidance on when to use this tool ('essential for material balance calculations, pressure transient analysis, and reserve estimation') and when not to use it ('confusing gas compressibility with oil compressibility'). It also lists common mistakes to avoid, effectively guiding usage versus 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, the description fully discloses behavior: it's a calculation tool (non-destructive, read-only implied), explains effects of parameters (e.g., H2S increases Tc/Pc), provides typical ranges and units, and details return structure. It also notes dependencies (used by gas_z_factor) and accuracy considerations (non-hydrocarbon effects).

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?

Well-structured with clear sections (Parameters, Pseudo-Critical Properties, Method Selection, etc.), but slightly verbose (e.g., repeating method details). Every sentence adds value (e.g., explaining non-hydrocarbon effects), though it could be more front-loaded; the core purpose is stated early, but some details are deep in the text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, 0% schema coverage, and an output schema (which the description aligns with by detailing returns), the description is highly complete: it covers purpose, usage, parameters, behavior, outputs, examples, and common pitfalls. It provides all necessary context for a calculation tool with multiple inputs and specific domain requirements.

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 0%, so the description compensates fully: it explains each parameter's purpose (e.g., sg for gas specific gravity), valid ranges, typical values, examples, and impacts on results (e.g., high H2S significantly affects Tc/Pc). It also details method options with recommendations, adding meaning beyond basic schema constraints.

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

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

The description clearly states the tool calculates pseudo-critical temperature and pressure for gas mixtures, specifying it's for real gases and required for Z-factor calculations. It distinguishes from siblings by focusing on gas properties (unlike oil or brine tools) and explicitly mentions it's used internally by gas_z_factor, avoiding overlap.

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 guidelines are provided: use for Z-factor calculations and gas property correlations, with method recommendations (PMC preferred, SUT for compatibility, BUR for specific apps). It warns against common mistakes like not accounting for non-hydrocarbons or using wrong gas gravity, and notes when to use alternatives (e.g., for pure components vs mixtures).

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 and excels. It details the density formula, behavior (e.g., 'Increases with pressure', 'Decreases with temperature'), typical ranges, and critical notes on units and conditions. It also warns about common mistakes, providing rich context beyond basic functionality.

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 sections like 'Parameters', 'Density Formula', and 'Common Mistakes', but it is lengthy with some redundant information (e.g., repeating parameter details in the example). While informative, it could be more front-loaded and concise, as not all sentences earn their place equally.

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 tool with 0% schema description coverage and no annotations, the description is highly complete. It covers purpose, parameters, formula, behavior, returns (though an output schema exists), common mistakes, and example usage. It provides all necessary context for an AI agent to use 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?

Given 0% schema description coverage, the description fully compensates by providing detailed parameter semantics. Each parameter is explained with descriptions, valid ranges, typical values, examples, and optionality. It adds meaning beyond the schema, such as the significance of 'zmethod' options and the impact of non-hydrocarbon fractions.

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's purpose with a specific verb ('Calculate') and resource ('gas density (ρg) at reservoir conditions'), distinguishing it from siblings like 'oil_density' or 'gas_compressibility'. It emphasizes this as a 'CRITICAL GAS PVT PROPERTY' for specific applications like gradient calculations and material balance.

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

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

The description provides clear context for when to use this tool (e.g., 'Essential for gradient calculations, well pressure analysis, and material balance') and includes a 'Common Mistakes' section that implicitly guides usage by highlighting pitfalls. However, it does not explicitly compare to alternatives like 'gas_z_factor' or specify when not to use it.

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 full burden and excels. It explains Bg behavior (decreases with pressure, increases with temperature), typical ranges (0.001-0.01 rcf/scf), formula details, return structure, common mistakes, and critical notes about using reservoir conditions. This provides comprehensive behavioral context beyond basic 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-structured with clear sections (Parameters, Bg Behavior, Formula, Returns, Common Mistakes, Example Usage, Note) and every sentence adds value. While comprehensive, it's appropriately sized for a complex tool with many parameters and no annotations, though slightly lengthy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, 7 parameters with 0% schema coverage, no annotations, but with output schema, the description is exceptionally complete. It covers purpose, parameters, behavior, formula, returns, common mistakes, examples, and critical usage notes, providing everything needed for correct tool 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?

With 0% schema description coverage, the description fully compensates by providing detailed parameter information: valid ranges, typical values, examples, optional/default values, and zmethod options. It adds significant meaning beyond the bare schema, including practical guidance like pressure must be absolute (psia) not barg/psig.

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

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

The description clearly states the tool calculates the gas formation volume factor (Bg), specifying it's a critical PVT property that computes the ratio of gas volume at reservoir to standard conditions. It distinguishes from siblings like oil_formation_volume_factor by explicitly mentioning gas-specific behavior and common confusion with oil FVF.

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

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

The description provides clear context for when to use this tool (material balance, reserve calculations, production forecasting) and mentions using the gas_z_factor tool for Z calculations. However, it doesn't explicitly state when NOT to use it or name specific alternative tools among siblings for related calculations.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It thoroughly explains the tool's behavior: it uses an 'iterative Newton-Raphson method' to solve for pressure, returns a dictionary with specific keys (value, method, units, inputs), and includes details on convergence ('Converges rapidly for well-posed problems'), error handling (e.g., parameter validity ranges), and consistency requirements (e.g., using the same Z-factor method throughout analysis).

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 sections like Parameters, P/Z Method Applications, Material Balance Principle, Solution Method, Returns, Common Mistakes, and Example Usage, making it easy to navigate. However, it is quite lengthy with extensive theoretical background (e.g., material balance equations), which, while informative, could be trimmed for more front-loaded conciseness without losing essential guidance.

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 is highly complete for this complex tool with no annotations and an output schema. It covers purpose, usage, parameters, behavior, return values, examples, and common pitfalls. Given the output schema exists (as per context signals), the description appropriately explains the return structure without redundancy, ensuring the agent has all necessary context to 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?

Given the schema description coverage is 0% (as indicated by context signals), the description fully compensates by providing detailed parameter semantics. It lists all parameters (pz, sg, degf, h2s, co2, n2, zmethod) with clear explanations, valid ranges, typical values, examples, and optional/default settings, adding significant meaning beyond the bare schema properties and required fields.

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's purpose: 'Calculate pressure from P/Z value' and 'Solves for pressure given a P/Z (pressure/Z-factor) value.' It specifically distinguishes this as a 'MATERIAL BALANCE TOOL' for gas material balance analysis, differentiating it from sibling tools like gas_z_factor or gas_critical_properties by focusing on iterative pressure calculation from P/Z inputs.

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 guidance on when to use this tool: 'Essential for gas material balance analysis where P/Z vs cumulative production is plotted.' It details applications such as volumetric gas reserves, aquifer influx detection, drive mechanism identification, and production forecasting, and warns against common mistakes like using separator temperature or wrong Z-factor methods, offering clear context for proper usage.

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 thoroughly explains the tool's behavior: it performs numerical integration ('The integration is performed numerically'), returns approximate but accurate results, outputs a dictionary with specific keys (value, method, units, inputs), and includes important behavioral notes like 'Always use reservoir conditions' and warnings about common mistakes (e.g., using wrong pressure units or temperature scales).

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 sections (Parameters, Pseudopressure Formula, Why Pseudopressure, Applications, Returns, Common Mistakes, Example Usage, Note) and uses bold headings for readability. While comprehensive, it is appropriately sized for a complex 8-parameter tool with no annotations. Some sections like 'Why Pseudopressure' could be slightly condensed, but overall it earns its length with valuable 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?

Given the tool's complexity (8 parameters, no annotations, but with output schema), the description is highly complete. It covers purpose, parameters, formula, rationale, applications, return structure, common mistakes, and example usage. The output schema existence means the description doesn't need to detail return values, but it still provides a helpful summary. This addresses all necessary context for accurate tool 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?

Given 0% schema description coverage (the schema has no descriptions for individual parameters beyond the request model), the description compensates fully by providing detailed parameter information. Each parameter is documented with type, required/optional status, valid ranges, typical values, examples, and semantic meaning (e.g., 'Gas specific gravity (air=1.0)', 'Reservoir temperature in °F'). This adds substantial value 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 clearly states the tool's purpose: 'Calculate gas pseudopressure difference (m(p))' with a specific verb ('Calculate') and resource ('gas pseudopressure difference'). It distinguishes from siblings by emphasizing this is a 'CRITICAL GAS ANALYSIS TOOL' for linearizing gas flow equations, unlike other gas property tools like gas_compressibility or gas_viscosity that compute individual properties.

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

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

The description provides clear context for when to use this tool: 'Essential for accurate gas well performance analysis' and lists specific applications like gas well testing, material balance, and reservoir simulation. However, it does not explicitly state when NOT to use it or name alternative tools for related calculations, though the sibling list includes tools like gas_rate_linear that might be alternatives in some contexts.

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 and excels. It explains the pseudopressure method, mathematical formulation, accuracy advantages over simplified Darcy's law, handling of pressure-dependent properties, and detailed return structure. It also covers important behavioral aspects like unit requirements (psia vs psig), typical value ranges, and error prevention through the 'Common Mistakes' section.

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 sections (Parameters, Flow Geometry, Pseudopressure Method, etc.) but is quite lengthy. While every section adds value, some information could potentially be more condensed. The front-loaded purpose statement is excellent, but the overall length pushes it slightly below perfect conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (11 parameters, specialized petroleum engineering domain), no annotations, and the presence of an output schema, the description is exceptionally complete. It covers purpose, usage context, mathematical foundation, parameter details, return values, common pitfalls, and example usage. The output schema existence means the description doesn't need to exhaustively document return structure, yet it still provides helpful context about the return dictionary.

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?

Despite 0% schema description coverage (parameters are nested under 'request'), the description provides comprehensive parameter documentation. Each parameter gets detailed explanations including physical meaning, units, validity ranges, typical values, examples, and special considerations (e.g., 'psd' can be scalar or array). This fully compensates for the schema's lack of descriptions and adds substantial value beyond basic parameter 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 explicitly states the tool's purpose: 'Calculate gas production rate for linear flow' with specific context about horizontal wells and real gas pseudopressure formulation. It clearly distinguishes from sibling tools like 'gas_rate_radial' by emphasizing linear flow geometry and contrasting with radial flow in the 'Linear vs Radial Flow' section.

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 guidance on when to use this tool versus alternatives. It specifies that linear flow occurs in horizontal wells, hydraulically fractured vertical wells, channelized gas reservoirs, and edge water drive systems, and contrasts linear flow with radial flow (which would use 'gas_rate_radial'). The 'Common Mistakes' section further reinforces proper usage scenarios.

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 full burden and excels. It discloses the mathematical method (pseudopressure formulation), explains what the calculation accounts for (Z-factor, viscosity variations), provides the flow formula, describes return format, lists common mistakes, and includes example usage. This gives comprehensive behavioral understanding.

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 sections (purpose, parameters, method, formula, returns, mistakes, example). While comprehensive, some sections like the detailed parameter list and common mistakes are lengthy but necessary for this complex tool. Every sentence adds value, though it could be slightly more front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 12-parameter engineering tool with no annotations, the description provides exceptional completeness. It covers purpose, methodology, parameters, formula, returns, common pitfalls, and examples. The output schema exists but the description still usefully explains return structure. This gives agents everything needed to use 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?

Despite 0% schema description coverage, the description provides extensive parameter documentation. Each parameter gets: purpose explanation, units, validity ranges, typical values, examples, and practical guidance (e.g., 'must be absolute' for pressure, 'should be well spacing/2' for drainage radius). This fully compensates for the schema gap.

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

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

The description clearly states the tool calculates gas production rate for vertical wells with radial flow geometry using real gas pseudopressure formulation. It distinguishes from sibling tools like 'gas_rate_linear' by specifying radial flow geometry and from 'gas_pseudopressure' by focusing on production rate calculation rather than pseudopressure alone.

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

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

The description provides clear context for when to use this tool (vertical wells with radial flow geometry, gas systems requiring pressure-dependent property accounting) and mentions it's more accurate than simplified Darcy's law. However, it doesn't explicitly state when NOT to use it or name specific alternative tools beyond the general comparison.

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 discloses behavioral traits. It explains the calculation method in detail, includes typical values and ranges, describes non-hydrocarbon effects on SG, specifies the return structure, and warns about common mistakes and constraints (e.g., 'Mole fractions must sum to 1.0').

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 sections but is overly verbose for a tool description. While all content is valuable, it includes extensive details like the full formula, typical hydrocarbon MW ranges, and multiple application examples that could be condensed. It's front-loaded with purpose, but later sections add bulk.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the calculation, no annotations, and an output schema (implied by the 'Returns' section), the description is highly complete. It covers purpose, usage, parameters, method, outputs, examples, and pitfalls, leaving no gaps for an AI agent to understand 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?

The schema description coverage is 0%, so the description must compensate, which it does excellently. It provides detailed parameter semantics: purpose, units, valid ranges, typical values, examples, and contextual meaning (e.g., 'hc_mw' as 'average MW of the hydrocarbon fraction, not individual component MW'). This goes far beyond what a bare schema would offer.

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's purpose: 'Calculate gas specific gravity from composition' using a specific method ('molecular weight weighted average'). It distinguishes from siblings like 'gas_sg_from_gradient' and 'weighted_average_gas_sg' by emphasizing compositional input rather than gradient or averaging of multiple SG values.

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 this tool: 'Essential when gas composition is known but SG measurement is unavailable or unreliable.' It also lists specific applications (e.g., 'Compositional Simulation,' 'Gas Plant Feed') and provides guidance on when not to use it via 'Common Mistakes' (e.g., 'Using weight fraction instead of mole fraction').

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 thoroughly explains the tool's behavior: it uses a 'Newton-Raphson iterative solver,' is a 'standalone fixed implementation' to avoid bugs, returns a dictionary with specific keys, and details sensitivity to inputs like temperature. It also covers constraints (e.g., gradient must be > 0) and typical use cases.

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 sections like 'Parameters,' 'Gradient Principle,' and 'Applications,' making it easy to navigate. It is appropriately sized for a complex tool, but some sections (e.g., 'Gradient Principle' formula) are detailed and could be slightly condensed without losing clarity. Overall, it's efficient and front-loaded with key 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?

Given the tool's complexity, no annotations, and an output schema (implied by 'Returns' section), the description is highly complete. It covers purpose, usage, parameters, behavioral details, applications, examples, and common mistakes. The output schema is described in the 'Returns' section, ensuring the agent understands the response format without redundancy.

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 schema description coverage is 0%, so the description must compensate. It provides detailed parameter semantics: 'gradient' as pressure gradient in psi/ft with typical ranges, 'degf' as temperature in °F with valid ranges, 'p' as pressure in psia, and 'method' as Z-factor method with options and recommendations. This adds significant meaning 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 clearly states the tool's purpose: 'Calculate gas specific gravity from pressure gradient.' It specifies the verb 'calculate' and the resource 'gas specific gravity' from 'pressure gradient,' and distinguishes it from sibling tools like 'gas_sg_from_composition' by focusing on gradient-based calculation rather than compositional analysis.

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 this tool: 'Essential for formation fluid identification and gas property verification when only gradient data is available.' It also provides context in the 'Applications' section, such as 'Formation Fluid ID' and 'Gas Density Verification,' and warns against common mistakes like using wrong units or temperatures, guiding proper usage.

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 full burden and excels. It explains the correlation method used, typical viscosity ranges (0.01-0.05 cP), how viscosity changes with pressure/temperature, the tool's accuracy advantages over ideal gas assumptions, and detailed return format. It also covers practical considerations like unit requirements and component accounting.

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 sections (Parameters, Viscosity Behavior, Correlation, Returns, Common Mistakes, Example) but is quite lengthy. While every section adds value, some information could be more condensed. The front-loading is good with purpose and criticality stated immediately.

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 calculation tool with 7 parameters, 0% schema coverage, and no annotations, the description provides exceptional completeness. It covers purpose, usage, parameters, behavior, methodology, return format, common mistakes, and examples. The output schema exists but the description still usefully explains the return structure and units.

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?

Despite 0% schema description coverage, the description provides comprehensive parameter documentation: valid ranges, typical values, examples, optional/default values, and practical explanations for each parameter. It adds significant meaning beyond the bare schema, including the 'zmethod' options with recommendation and clarification that 'p' can be scalar or array.

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

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

The description clearly states the tool calculates gas viscosity using the Lee, Gonzalez & Eakin correlation, specifying it's for natural gas at reservoir conditions. It distinguishes itself from sibling tools like 'oil_viscosity' by explicitly contrasting gas vs. oil viscosity behavior and mentioning it's a critical PVT property for flow rates and pressure drops.

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 guidance on when to use this tool vs. alternatives: it specifies it's for gas (not oil), at reservoir conditions (not separator conditions), and uses real gas behavior (not ideal gas). It also warns against common mistakes like using wrong temperature units or pressure types, which implicitly defines when not to use it.

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 excels by disclosing behavioral traits: it explains the correlation method (McCain 1990), valid ranges, typical outputs (5-200 lb/MMSCF), critical applications, common mistakes, and return structure. It also details how water content behaves with pressure and temperature changes, providing comprehensive operational context.

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 sections (Parameters, Water Content Behavior, Applications, Returns, etc.), but it is lengthy. Every sentence adds value, such as explaining hydrate formation and common mistakes, but it could be more front-loaded; the core purpose is stated early, but some details might be condensed for better conciseness without losing essential 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?

Given the complexity of the tool (engineering calculation with critical safety implications), no annotations, and an output schema that documents return values, the description is complete. It covers purpose, usage, parameters, behavior, applications, returns, and common pitfalls, providing all necessary context for an AI agent to invoke the tool correctly and understand its significance in gas processing.

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 0%, so the description must compensate fully. It adds extensive meaning beyond the bare schema: defines each parameter (sg, degf, p) with units, valid ranges, typical values, examples, and behavioral effects (e.g., water content decreases with increasing pressure). This thoroughly documents all parameters, making the tool's inputs clear and actionable.

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 specific purpose: 'Calculate water content of natural gas' with the verb 'calculate' and resource 'water content of natural gas'. It distinguishes from siblings by focusing on water content calculation specifically for hydrate prevention and dehydration design, unlike other tools that handle properties like compressibility, density, or viscosity.

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 guidance is provided on when to use this tool: 'Essential for hydrate prevention, dehydration unit design, and pipeline operation.' It also specifies alternatives implicitly by mentioning related concepts (e.g., water dew point) and contexts where it's critical, such as pipeline operation vs. LNG processes, helping differentiate from sibling tools that might calculate other gas properties.

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 thoroughly explains the tool's behavior: 'Z-Factor Behavior' section describes how Z varies with pressure, 'Non-Hydrocarbon Effects' explains how inputs affect results, 'Returns' details the output structure, and 'Common Mistakes' lists critical usage pitfalls. This covers behavioral aspects like input validation, output format, and error-prone scenarios.

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 sections (Parameters, Z-Factor Behavior, Method Selection, etc.), making it easy to navigate. However, it is quite lengthy (over 500 words), which may be excessive for some contexts. Every sentence adds value, but it could be more front-loaded by moving the 'Returns' section earlier. The efficiency is high, but the overall size slightly impacts conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (multiple parameters, no annotations, 0% schema coverage), the description is exceptionally complete. It covers purpose, usage, parameters, behavior, method selection, output format, common mistakes, and examples. The presence of an output schema (implied by 'Has output schema: true') is complemented by the detailed 'Returns' section. No gaps remain for effective tool 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 0%, so the description must fully compensate. It provides extensive parameter semantics: each parameter is documented with purpose, valid ranges, typical values, examples, and effects on calculation (e.g., 'H2S and CO2 increase Z-factor'). The 'Parameters' section adds meaning beyond basic schema types, including practical guidance like 'must be absolute' for pressure and 'separator gas gravity' for sg.

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

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

The description explicitly states the tool's purpose: 'Calculate gas compressibility factor (Z-factor).' It distinguishes this tool from siblings by specifying it's for gas (not oil/brine) and focuses on a specific PVT property, unlike general calculation tools in the list. The opening section emphasizes its critical role in gas reservoir calculations.

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

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

The description provides explicit guidance on when to use this tool vs. alternatives. It states: 'Essential for all gas reservoir calculations including material balance, reserve estimation, and flow calculations,' and includes a 'Method Selection' section with recommendations (e.g., 'DAK recommended,' 'Use for: All applications, high accuracy requirements'). It also warns about limitations: 'For sour gas (H2S > 5%), use Wichert-Aziz correction (not included here).'

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 thoroughly explains what the tool does (creates dimensionless aquifer influence functions), the integration method (numerical integration with Gaussian quadrature), output format (dictionary with specific keys), and practical considerations like common mistakes and scaling requirements. This provides comprehensive behavioral context beyond basic functionality.

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 sections (Parameters, Background, Applications, etc.), but it's quite lengthy with multiple paragraphs that could be more streamlined. While all content is relevant, some sections (like extensive background theory) might be more detailed than necessary for tool selection, affecting conciseness despite good organization.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (aquifer modeling with multiple parameters), no annotations, and an output schema that exists but isn't detailed here, the description provides exceptional completeness. It covers purpose, parameters, methodology, outputs, applications, common mistakes, examples, and integration instructions, making it fully self-contained for understanding and using the tool effectively.

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?

Despite 0% schema description coverage (the schema has only one parameter 'request' with nested properties), the description compensates fully by detailing four key parameters (res, start, end, rows) with their meanings, constraints, typical ranges, examples, and physical interpretations. It also covers additional parameters from the schema (like infl, ei, piston) in the background and application sections, providing substantial semantic value 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 explicitly states the tool generates Van Everdingen & Hurst aquifer influence functions for AQUTAB keyword in ECLIPSE/Intersect, specifying both the action ('generate') and resource ('aquifer influence functions'). It clearly distinguishes this from sibling tools by focusing on aquifer modeling rather than fluid properties or other reservoir engineering calculations.

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

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

The description provides clear context for when to use this tool (aquifer modeling, material balance, pressure maintenance, etc.) and mentions integration with ECLIPSE. However, it does not explicitly state when NOT to use it or name specific alternatives among the sibling tools, though the specialized nature implies it's for aquifer-specific calculations.

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

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

With no annotations provided, the description carries full burden and does well by explaining key behaviors: it generates tables with logarithmic pressure spacing, finer near bubble point; optionally exports ECLIPSE files; calculates missing values (pb, rsb) when not provided; and returns a dictionary with table, summary, columns, etc. It doesn't mention computational cost or rate limits, but covers most operational aspects thoroughly.

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 sections (Parameters, Generated Properties, Table Structure, etc.) and front-loads the core purpose. While comprehensive, some sections like the detailed parameter documentation are necessarily lengthy given the complexity. Every sentence adds value, though it could be slightly more concise in the 'Common Mistakes' and 'Example Usage' sections.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (13 parameters, no annotations, but has output schema), the description is remarkably complete. It explains what the tool does, when to use it, all parameters thoroughly, generated properties, table structure, export functionality, return format, common mistakes, and includes a full example. The output schema existence means it doesn't need to exhaustively document return values, which it appropriately references.

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 0%, so the description must fully compensate - and it does excellently. Each parameter is documented with meaning, units, validity ranges, examples, defaults, and practical notes (e.g., 'If 0, auto-calculates', 'Typical: 0.6-1.2', 'More rows = finer resolution'). It adds significant value beyond what a bare schema would provide, explaining parameter interactions and recommendations.

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's purpose: 'Generate comprehensive black oil PVT table' with specific properties (Rs, Bo, μo, ρo, Co) and pressure range (14.7 psia to specified maximum). It distinguishes from siblings by emphasizing it's 'the most comprehensive PVT tool' for 'complete tables for reservoir simulation input or analysis', unlike simpler property calculators in the sibling list.

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 this tool ('Use for complete reservoir analysis or simulation input preparation') and provides alternatives by noting it's 'the most comprehensive PVT tool', implying simpler sibling tools like 'oil_bubble_point' or 'oil_solution_gor' might be used for specific calculations. It also includes 'Common Mistakes' section with practical guidance on parameter settings.

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 full burden and excels at behavioral disclosure. It explains the mathematical method (Dykstra-Parsons log-normal distribution), output structure, common mistakes, limitations (idealized properties vs actual reservoir data), and specific constraints like layer sorting and equal thickness assignment.

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 comprehensive but lengthy with some redundancy (usage example appears twice). While well-structured with clear sections, it could be more concise by eliminating repetition and tightening some explanations without losing essential 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?

Given the tool's complexity, no annotations, and rich output schema, the description provides complete context. It explains the method, output structure, applications, limitations, and practical considerations, making it fully self-contained for an AI agent to understand and use 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?

Despite 0% schema description coverage, the description provides extensive parameter documentation including purpose, valid ranges, typical values, examples, and practical guidance. It covers all parameters (lorenz, nlay, k_avg, h) and explains their relationships and constraints beyond what the bare schema provides.

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

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

The description clearly states the tool generates layered permeability distributions from a Lorenz coefficient, specifying it creates detailed layer-by-layer permeability and thickness distributions. It distinguishes from siblings by focusing on reservoir simulation model building and waterflood prediction, which none of the sibling tools mention.

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

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

The description provides clear context for when to use this tool (reservoir simulation, waterflood prediction, conformance studies, etc.) and includes a 'Critical for' section with specific applications. However, it doesn't explicitly state when NOT to use it or name specific alternative tools among siblings.

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 full burden and does an excellent job explaining what the tool does: generates tables for reservoir simulation, describes the mathematical models (Corey and LET formulas), explains output format, and provides practical guidance. It doesn't mention rate limits, authentication needs, or computational cost, but covers the core behavior thoroughly.

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 comprehensive but quite long with multiple sections (Parameters, Correlation Families, Table Types, etc.). While all content is valuable, it could be more front-loaded with critical information. The structure is logical but not optimally concise for quick scanning by an AI 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 complexity of the tool (multiple correlation models, table types, and many parameters) and the presence of an output schema, the description is exceptionally complete. It covers purpose, usage, parameters, mathematical background, workflow, return values, common mistakes, and examples. The output schema existence means the description doesn't need to detail return structure, allowing focus on conceptual guidance.

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 schema description coverage is 0% (all parameters are in a nested 'request' object with no descriptions at the top level), but the description compensates fully with detailed parameter documentation. Each parameter gets clear explanations, typical ranges, examples, and context about when they're required (e.g., which parameters apply to Corey vs LET, SWOF vs SGOF). This adds substantial meaning 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 clearly states the tool's purpose: 'Generate relative permeability table for reservoir simulation' with specific details about creating saturation-dependent curves for named simulators (ECLIPSE, Intersect, CMG). It distinguishes from sibling tools by focusing on relative permeability table generation, which is unique among the listed reservoir engineering 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 provides explicit guidance on when to use different correlation families (Corey for quick estimates/standard cases, LET for history matching/complex curves), table types (SWOF for water-oil, SGOF for gas-oil, SGWFN for three-phase), and includes a detailed workflow section. It also lists common mistakes to avoid, giving clear usage boundaries.

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 excels by disclosing key behavioral traits. It details the database source (NIST, API), explains that properties are EOS-specific, warns about common mistakes (e.g., misspellings, wrong EOS), and provides usage guidance (e.g., PR79 recommended). This goes beyond basic functionality to include operational context and limitations.

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

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

The description is front-loaded with the core purpose but includes extensive sections (e.g., 'Available Components,' 'EOS Models,' 'Applications') that, while informative, could be streamlined. Some sentences, like detailed lists of components, may not all earn their place for conciseness, though the structure is organized with headings for clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (database lookup with EOS-specific properties), no annotations, and an output schema present, the description is highly complete. It covers purpose, parameters, returned properties, usage scenarios, common mistakes, examples, and notes, providing all necessary context for an AI agent to use the tool effectively without relying on structured 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 0%, so the description must compensate fully. It does so by elaborating on both parameters: for 'component,' it provides examples, notes case-insensitivity, and lists available components; for 'eos,' it explains options, default, and recommendations. This adds significant meaning beyond the bare schema, ensuring parameters are well-understood.

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's purpose: 'Get critical properties for hydrocarbon components from database.' It specifies the verb 'Get' and the resource 'critical properties for hydrocarbon components,' distinguishing it from sibling tools like 'gas_critical_properties' or 'oil_twu_critical_properties' by focusing on a database lookup for compositional analysis rather than calculations or specific fluid types.

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

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

The description provides clear context on when to use this tool, such as for 'compositional analysis, EOS calculations, and phase behavior modeling,' and lists applications like 'Compositional Simulation' and 'Flash Calculations.' However, it does not explicitly state when not to use it or name specific alternatives among sibling tools, though it implies alternatives for components not in the database.

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 full burden and excels. It details the calculation algorithm step-by-step, provides interpretation guidelines (L < 0.3: high conformance, etc.), lists common mistakes with specific validation requirements (sum to 1.0, length match), and explains what the tool returns. This gives the agent comprehensive behavioral understanding.

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 sections (Parameters, Input Data Sources, Calculation, Interpretation, Applications, Returns, Common Mistakes, Example Usage, Note). While comprehensive, some sections like 'Applications' and 'Common Mistakes' are quite detailed, making it longer than minimal. However, every sentence adds value, and key information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, 0% schema description coverage, but with an output schema, the description provides exceptional completeness. It covers purpose, usage, algorithm, interpretation, applications, parameters, returns (though output schema exists, it adds interpretation guidance), common mistakes, and examples. This fully compensates for the lack of structured metadata.

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?

Despite 0% schema description coverage, the description provides extensive parameter semantics. It defines flow_frac and perm_frac with clear units (0-1 fractions), requirements (must sum to 1.0, length match), examples, and explains their physical meaning (flow fractions from production allocation, permeability-thickness fractions). It also clarifies common pitfalls like using weight fractions instead of flow fractions.

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

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

The description clearly states the tool calculates Lorenz coefficient from flow and permeability fractions, specifying it's for analyzing production data and quantifying vertical conformance. It distinguishes from sibling 'flow_fractions_from_lorenz' by being the inverse operation, and from 'beta_to_lorenz' and 'lorenz_to_beta' by using different input types.

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 this tool ('most direct way to calculate Lorenz from actual production data') and provides extensive context through 'Input Data Sources' (PLT, tracer tests, etc.) and 'Applications' sections. It also implicitly contrasts with siblings by focusing on measured production allocation rather than theoretical distributions.

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