MaCalculatriceEnLigne

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

With no annotations, the description carries the full burden. It discloses the formula (Epley) and return fields, but lacks details on limitations, edge cases, or behavior beyond the formula (e.g., handling outliers). The disclosure is adequate but not thorough.

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

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

The description is concise with two sentences: first states purpose, second mentions return value and cross-reference. No wasted words, 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?

The description claims a 'full 1RM-to-12RM repetition table' but the return example only lists three fields (input_weight, input_reps, estimated_1rm), suggesting a possible inconsistency. It fails to clarify whether the output truly includes a table structure. Given this gap, completeness is inadequate.

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

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

Schema coverage is 100%, so the description adds minimal parameter-level info beyond explaining that inputs represent a 'known lift'. Baseline 3 is appropriate as the schema already describes parameters well.

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 a 'full 1RM-to-12RM repetition table' using the Epley formula, specifying the verb 'Generate' and resource. It distinguishes itself from sibling 'calculate_one_rep_max' by creating a table rather than a single value.

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 implicitly suggests usage by mentioning 'from a known lift' and references 'list_bundles' for related sport calculators, but does not explicitly state when to use this tool versus alternatives like 'calculate_one_rep_max' or provide exclusions.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the operation (addition) and the output format (hours and minutes), but does not address potential edge cases like overflow (e.g., minutes exceeding 59) or whether the tool handles carry-over. For a simple additive tool, the description is adequate but lacks depth.

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 consists of two concise sentences that front-load the primary purpose and then efficiently direct users to related tools. Every word serves a purpose, with no redundancy or unnecessary detail.

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

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

Given the tool's simplicity (four parameters, straightforward addition) and the presence of an output schema (not shown but noted as present), the description is nearly complete. It states the output in hours and minutes, but could briefly mention that minutes are constrained to 0-59 and that carry-over is handled. Overall, it covers the essential 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?

The input schema has 100% description coverage for all four parameters (hours1, minutes1, hours2, minutes2), making the schema self-sufficient. The description adds no extra meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

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

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

The description clearly states the tool's function: 'Add two time durations and return the total in hours and minutes.' It uses specific verbs and resources, and the mention of 'list_bundles' for related 'temps-rh' calculators distinguishes it from sibling tools. The purpose is unambiguous 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 a hint by referencing 'list_bundles' for related calculators, implying that other time-related operations may be available there. However, it does not explicitly state when to use this tool versus alternatives (e.g., for subtraction, conversion, or more complex duration arithmetic). The guidance is minimal and could be improved by clarifying its specific scope.

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

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

No annotations are provided, so the description carries full responsibility. It lists the returned fields, which implies a read-only, deterministic operation. While it does not explicitly state safety or authorization needs, the nature of the calculation suggests low risk. The output structure is well-described, adding 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 concise, consisting of two sentences that efficiently convey the tool's function and output. The first sentence states the purpose and includes key details, and the second provides a helpful cross-reference. No wasted words.

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 simple parameter set (one required string), the existence of an output schema (implied by the description), and a large sibling list, the description is complete. It covers what the tool does, what it returns, and where to find related calculators. No gaps remain.

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

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

The input schema has 100% coverage with a single parameter described as 'YYYY-MM-DD — Date of birth'. The description does not add further meaning beyond what the schema already provides. Since coverage is high, the baseline score of 3 is appropriate.

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

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

The description clearly states the tool calculates exact age in years, months, and days from a birth date. It specifies the verb 'calculate' and the resource 'age', and distinguishes itself from siblings by providing specific output fields and referencing related calculators via list_bundles.

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 includes a reference to list_bundles for related calculators, hinting at alternative tools like calculate_age_in_units, but it does not explicitly state when to use this tool versus others or provide contextual prerequisites. More guidance on when to use this precise age calculation would improve the score.

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

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

No annotations provided, so description carries full burden. It does not disclose how leap years, time zones, or future dates are handled. Only states 'Calculate exact age' without behavioral details.

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

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

Two sentences, front-loaded with purpose, and efficiently references sibling tool list. No unnecessary words.

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?

Simple tool with one parameter and output schema implied. Description covers purpose and output but lacks behavioral details. Adequate but not thorough.

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

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

Schema coverage is 100% and includes format description. The description adds context about output units but does not significantly enhance parameter meaning beyond the schema.

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

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

Clearly states the verb 'calculate', resource 'exact age in multiple units from birth date', and distinguishes from sibling tools like 'calculate_age' by specifying the output units (weeks, hours, minutes, seconds).

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?

Implies usage for age in small units, but does not explicitly state when to use this tool over alternatives like 'calculate_age'. No exclusions or prerequisites mentioned.

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

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

With no annotations, the description must fully disclose behavior. It correctly states that the tool computes units and grams, but omits any details about side effects, permissions, or limitations. For a simple calculator, this is adequate but not detailed.

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 extremely concise with two sentences that front-load the core purpose. Every sentence adds value without redundancy.

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

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

For a straightforward calculation tool with an output schema available, the description covers the essentials: what it computes, when to use it, and the inputs. It could be slightly more complete by mentioning that multiple drinks can be analyzed, but it is largely sufficient.

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

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

Schema description coverage is 0%, so the description must compensate. It mentions 'Inputs: volume mL, ABV %' but does not explain the array structure, the 'type' field, or that multiple drinks can be input simultaneously. This insufficiently fills the gap left by missing schema descriptions.

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

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

The description clearly states it computes UK alcohol units and grams of pure alcohol for health tracking and limit awareness. It distinguishes from sibling tools by specifying 'UK units' and mentioning 'standard-drink equivalent', but does not explicitly differentiate from other alcohol-related calculators like calculate_blood_alcohol.

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 says 'Use for health tracking and limit awareness,' which provides some usage context. It mentions a related tool group (list_bundles for cuisine calculators) but does not specify when not to use this tool or name alternatives for similar calculations, leaving gaps in guidance.

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

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

No annotations are provided, so the description carries the full burden. It does not disclose any behavioral traits such as side effects, permissions, rate limits, or whether the tool is destructive. The description is purely functional.

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 two sentences with no wasted words. It front-loads the purpose, then provides the return structure and a cross-reference, making it efficient and easy to parse.

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 single-parameter tool with an output described, the description covers purpose, return, and a sibling reference. However, it lacks behavioral information and details on output interpretation, making it adequate but not fully comprehensive.

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

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

The input schema has 100% coverage with a description for altitude_m. The description does not add additional meaning beyond the schema, so baseline 3 applies.

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

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

The description clearly states it assesses altitude sickness risk and recommends acclimatization schedules. It also specifies the return object. While the verb and resource are specific, it does not explicitly contrast with sibling calculators, though the name is unique enough.

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 mentions 'See list_bundles for related ''voyage'' calculators,' providing a pointer to related tools. However, it lacks explicit conditions on when to use this tool versus others or 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?

No annotations provided, but the tool is a straightforward unit conversion with no side effects. The description does not add behavioral details beyond the basic operation, which is acceptable for such a non-destructive tool.

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

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

The description is extremely concise: two short sentences directly communicating the purpose, units, return format, and a hint to related tools. Every word earns 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 simplicity of the tool and the presence of an output schema, the description adequately covers the conversion intent and units. The placeholder return format is minor; overall, it provides sufficient context for a basic converter.

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

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

The input schema provides full descriptions for all three parameters (100% coverage), so the description adds minimal additional meaning. It confirms allowed units but doesn't elaborate beyond the schema.

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

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

The description clearly states the tool converts angles among degrees, radians, gradians, and turns, matching the verb and resource. The placeholder '{original}' in the return format is slightly ambiguous, but doesn't detract from understanding the primary purpose.

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 indirectly points to related tools via list_bundles, but does not explicitly state when to use this converter over sibling convert_* tools. A clearer directive would improve selection.

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

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

With no annotations, the description carries the full burden. It describes the calculation and return values but omits behavioral traits like assumptions (e.g., payment timing, compounding frequency) or safety aspects. Basic but not comprehensive.

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

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

Two efficient sentences: first states purpose, second lists returns and references a bundle. No extraneous text, but could be marginally improved by front-loading key details.

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 provides the return shape but lacks details such as default payment timing, rate conversion, or rounding behavior. For a standalone financial calculator, more context would improve usability.

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

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

All three parameters have descriptive schema comments (principal in EUR, rate as annual percent, periods in months). The description adds no further meaning, so baseline 3 applies given 100% coverage.

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 it calculates periodic payment amount for a loan or annuity and specifies the return structure. However, it does not distinguish this tool from similar siblings like calculate_loan_payment or calculate_mortgage, which could cause confusion.

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 references list_bundles for related calculators, implying a context but not explicitly stating when to use this tool versus alternatives. No when-not or direct alternative guidance is provided.

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

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

No annotations are provided, so the description carries the full burden. It only mentions 'AI-powered' and the subscription requirement, but does not disclose any behavioral traits such as whether it is read-only, error handling, latency, or rate limits. For a generative AI tool, more transparency is needed.

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

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

Two sentences, each serving a distinct purpose: stating the tool's function and noting the subscription requirement. No wasted words.

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 that an output schema exists (as per context signals), the description does not need to detail return values. It covers the core purpose and a key requirement. However, it could hint at the breadth of calculations to set expectations better.

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

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

Schema description coverage is 100%, with both parameters having descriptions in the JSON schema. The description adds little beyond stating it is a 'universal calculator', so the baseline of 3 is appropriate.

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

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

The description clearly states it is a 'universal AI-powered calculator' for 'any calculation not covered by specialized tools', which distinguishes it from the many sibling tools. The verb 'handles' and resource 'calculation' are specific.

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 when-to-use guidance ('not covered by specialized tools') and a prerequisite ('Requires premium subscription'). It does not explicitly list alternatives, but given the hundreds of sibling tools, the implication to use them first is clear.

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

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

No annotations are present, so the description must fully disclose behavior. It mentions input units (cm) and output (L and gallons), but it incorrectly implies a shape parameter (rectangular/cylindrical/bow-front) that is not in the schema. It also fails to explain the 'substrate_cm' parameter's effect on volume, causing confusion.

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

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

The description is concise with two sentences, beginning with the core purpose. The reference to 'list_bundles' adds slight overhead but is helpful. Overall, it is structured well and 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 the presence of 4 parameters (including substrate) and an output schema, the description should cover how substrate affects calculation and clarify the shape ambiguity. It fails to address these, leaving gaps for an agent relying solely on the description.

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%. The description provides some meaning for length, width, height (L×W×H in cm) but introduces a non-existent shape attribute and omits explanation of 'substrate_cm'. This mismatch reduces the utility of the description for parameter understanding.

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

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

The description clearly states the tool computes aquarium water volume in L and US gallons for fishkeeping, dosing, and stocking decisions. The verb 'compute' and resource are specific, and it points to a sibling tool for related calculators, distinguishing its focus.

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 mentions use cases (fishkeeping, dosing, stocking) and references 'list_bundles' for related calculators. However, it does not explicitly state when to prefer this tool over other volume calculators like 'calculate_volume' or 'calculate_pool_volume', leaving some ambiguity.

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

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

No annotations provided, so the description must carry the burden. It mentions input and output (returns area in input-units squared) but lacks details on error handling, shape validation, or limitations like precision. Adequate but not thorough.

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

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

Two concise sentences that front-load the core functionality and add strategic context (use cases, pointer to list_bundles). No unnecessary words.

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 (10 parameters, many shapes) and the presence of an output schema (not shown), the description covers basic usage and return format. Missing shape-specific parameter guidance (e.g., which dimensions needed for each shape), but overall sufficient for a simple calculation 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?

Input schema has 100% parameter description coverage, and the description only adds generic 'shape + dimensions' which is redundant. No additional meaning or hints beyond the schema.

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

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

Clearly states the tool computes area for 2D shapes, lists common examples, and mentions use cases. However, it does not explicitly differentiate from sibling tools like calculate_volume or calculate_perimeter, though the specific verb+resource ('compute area') is clear.

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

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

Provides context for when to use (geometry, real estate, paint estimates) and references list_bundles for related calculators. Does not explicitly state when not to use or compare to alternatives, but the guidance is clear.

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

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

No annotations provided, and the description only states the tool's purpose and return fields. Fails to disclose any behavioral traits like handling of edge cases (e.g., zero revenue), category-specific calculations, or if it is read-only. Limited 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?

Two sentences, front-loaded with purpose and return structure, and a pointer to related tools. No wordiness; every sentence serves a purpose.

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?

Covers the main aspects: what it calculates, return fields, and reference to related calculators. Could be improved by explaining the impact of different categories (vente, service_bic, etc.). Good given the tool is straightforward and has an output schema.

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

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

Input schema (100% coverage) already describes both parameters adequately. Description adds no additional meaning or context beyond listing return fields, so baseline score of 3 is appropriate.

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

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

Clearly states it calculates auto-entrepreneur net income and social charges, and lists return fields. Implicitly distinguishes from siblings via reference to 'finance-france' calculators, but no explicit differentiation.

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?

Implies use for auto-entrepreneur calculations but provides no explicit when-to-use or when-not-to-use guidance. References list_bundles for related tools, but no direct alternatives or exclusions.

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 must fully disclose behavioral traits. It only states 'Returns mean and detail' without mentioning safety (read-only), rate limits, authentication needs, or any side effects. This is minimal disclosure for a tool with no annotations.

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 short (two sentences) and uses bullet-like structure, but it includes inaccurate information (mode parameter) and vague phrasing ('Returns mean and detail'). It could be more precise and accurate without extra length.

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 supports four types of averages, the description does not explain the differences or when to use each. An output schema exists, so return details are partially covered, but the missing 'mode' parameter and lack of behavioral context leave the description incomplete.

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 100% schema coverage, the baseline is 3, but the description introduces a nonexistent 'mode' parameter, misrepresenting the actual schema. It adds little beyond the schema's 'Array of numbers' and 'Optional weights for weighted average', and the inaccuracy reduces the value.

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?

Description states 'Compute simple, weighted, geometric, or harmonic mean' which clearly identifies the tool's purpose. However, it mentions a 'mode' parameter that does not exist in the input schema, causing confusion. It does not explicitly differentiate from the many sibling calculate_ tools, only referring to a bundle for related calculators.

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

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

The description suggests use cases like 'grade averages, returns, or rates' and points to list_bundles for related calculators. It lacks explicit guidance on when not to use this tool or comparisons to specific siblings, leaving the agent to infer from the large sibling list.

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 must disclose behavioral traits. It says 'estimate' and 'returns weighted average and mention,' but does not explicitly state it is a read-only calculation with no side effects. The lack of detail on any constraints or potential issues leaves behavioral transparency weak.

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

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

The description is concise with two sentences. The first sentence states the purpose, and the second provides usage context and a reference to related tools. No unnecessary words or redundancy.

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

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

Given the complexity (7 required parameters, output schema exists), the description is adequate but not comprehensive. It explains the tool's purpose and output but lacks details on the calculation process or any prerequisites. The mention of 'weighted average and mention' is helpful, but more context on the Bac grading system would improve completeness.

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

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

The input schema already provides detailed descriptions for all 7 parameters with 100% coverage, including ranges and coefficients. The description's mention of 'grades by subject' adds no meaningful detail beyond the schema, so the baseline score of 3 is appropriate.

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

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

The description clearly states the tool estimates the French Baccalauréat final score using grades and coefficients. The verb 'estimate' and specific resource 'French Baccalauréat final score' make the purpose unambiguous. It does not explicitly differentiate from similar tools like calculate_brevet_points, but the subject is distinct enough.

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 mentions using it to track lycée results before official scores, providing a clear use case. However, it does not specify when not to use it or directly compare with alternatives, only hinting at related education calculators via list_bundles.

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

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

Annotations are absent, so the description carries the burden. It states it returns an adjusted recipe but doesn't elaborate on output structure (although output schema exists). It doesn't mention auth, rate limits, or side effects, but for a calculation tool, this is acceptable.

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 two sentences with no wasted words. It front-loads the core action and context, then provides necessary additional context about inputs, output, and related tools. Highly efficient.

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

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

Given the 5 required parameters and existence of output schema, the description covers the tool's purpose, input categories, output nature, and related resources. It is nearly complete; only minor detail like mentioning the output schema type might be added, but not necessary.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by grouping parameters (altitude m, ingredients) and clarifying the high-level role of inputs beyond the schema's individual descriptions. This aids understanding without being redundant.

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 verb 'Adjust' and the resource 'baking recipe for high altitude', providing a specific purpose. It distinguishes from sibling tools by emphasizing altitude adjustment and referencing related calculators in list_bundles.

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

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

The description explicitly says 'Use for mountain cooking', which indicates context of use. It also points to list_bundles for related cuisine calculators, offering direction for alternatives. However, it does not specify when not to use or provide explicit exclusions.

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

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

No annotations provided, and the description lists inputs ('value, from-unit, to-unit') that don't exist in the schema, creating mismatch. No disclosure of behavioral traits like supported units or output format.

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 short but contains inaccurate information, making it inefficient. Key details are missing, and the input list is misleading.

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?

Fails to explain actual usage (only cups input, enum ingredients, output unit). No output schema provided, and the description omits critical context for a tool with this complexity.

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 parameters (ingredient, quantity_cups) are not explained; instead, nonexistent parameters are mentioned. With 0% schema coverage, the description adds no meaningful guidance and actively misleads.

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

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

The description states 'convert baking measurements' but the input schema only accepts 'quantity_cups', contradicting the claim of converting from any unit. This vagueness fails to accurately represent the tool's scope.

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

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

The description suggests using for recipe translation and references 'list_bundles', but does not differentiate from siblings like 'convert_cooking' or 'calculate_cooking_conversion'.

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

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

No annotations provided, so description carries full burden. It discloses the return format but does not mention any potential side effects, limitations (e.g., input length), or error handling. Adequate for a simple conversion tool.

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

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

Two sentences: first covers purpose and scope, second mentions return format and references related tools. No unnecessary words, efficient and 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 that an output schema exists (context signals indicate true), the description mentions the return fields. Combined with full schema documentation and simple tool behavior, the description is complete.

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

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

Schema coverage is 100% with clear descriptions for each parameter. The description adds no additional parameter meaning beyond what the schema already provides. Baseline score applies.

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

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

The description clearly states the tool's action: 'Convert numbers between bases' with explicit scope (binary, octal, decimal, hexadecimal, any base 2-36). It differentiates from siblings by listing common bases and mentioning the related bundle.

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

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

Provides a reference to list_bundles for related math calculators but lacks explicit guidance on when to use this tool versus alternatives like calculate_number_base_convert. No when-not-to-use conditions.

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

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

No annotations provided. Description does not disclose behavioral traits beyond computation. Calculator tool implies read-only, but not stated; adequate for a simple 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?

Two sentences, no waste, includes return structure and cross-reference to related tools. Efficient and 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?

Complete for a calculator: names outputs, references related bundle, covers all needed info despite no output schema provided.

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

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

Schema coverage is 100% with descriptions. Description adds context about UDL and output, but does not significantly enhance parameter meaning beyond 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?

Specific verb+resource: 'Calculate max bending moment and shear for a beam under uniform distributed load.' Clearly distinguishes from other calculators by specifying UDL and returns. Sibling differentiation via reference to list_bundles for related construction calculators.

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

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

Describes what is calculated and returns, and points to list_bundles for related tools. Lacks explicit when-to-use or when-not-to-use statements, but context is clear.

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, and the description only mentions the output fields. It does not disclose behavioral traits such as whether the tool is read-only, if it requires authentication, or any side effects. For a calculator that likely has no destructive actions, the description lacks 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 exceptionally concise with only two sentences. The first sentence clearly states the purpose and expected output, while the second points to related tools. Every word serves a purpose, making it highly efficient.

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

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

The description covers the essential purpose and output for a simple calculator. However, it could be improved by mentioning the tax year or legal basis for the calculation. Given that an output schema is present (the listed return fields), the description is mostly complete.

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

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

The input schema already provides descriptions for all three parameters (catalog_value, co2, fuel_type) with 100% coverage. The description adds no additional meaning beyond what is in the schema, so the baseline score of 3 is appropriate.

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

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

The description clearly states the specific verb 'Calculate' and the precise resource 'Belgian benefit-in-kind for company car (avantage de toute nature voiture)'. It also lists the return fields, making the tool's purpose unambiguous.

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

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

The description suggests seeing list_bundles for related 'finance-belgique' calculators, which implies a broader context but does not explicitly state when to use this tool versus alternatives or any prerequisites. No 'when to use' or 'when not to use' guidance is provided.

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

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

The description discloses that the tool returns tax due and effective rate, and implies no side effects. With no annotations provided, this is adequate transparency for a calculation tool.

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

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

Three concise sentences: purpose, use case, inputs/outputs, and reference to related tools. Efficient and well-structured.

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

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

The description covers core behavior and references outputs, but the missing region parameter in schema versus description creates a gap in completeness. Output schema exists, so return values need not be detailed further.

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 description mentions 'region' as an input, but the input schema does not include a region parameter. This discrepancy reduces clarity and may mislead agents. Schema coverage is 100% but description adds inconsistent info.

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

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

The description clearly states the tool computes Belgian donation tax by region, for estate planning, and specifies inputs and outputs. It distinguishes itself from siblings by focusing on Belgian donation tax with regional variation.

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

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

It provides a clear use case (estate planning in Belgium) and points to related tools via list_bundles. However, it does not explicitly exclude other contexts or mention alternatives for other tax calculations.

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

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

No annotations are provided, so the description carries the full burden. The description does not disclose behavioral traits such as idempotency or side effects, but since it's a pure calculation, minimal disclosure is acceptable. No contradiction with annotations.

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

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

Two sentences: first states purpose and output, second directs to related tools. No unnecessary words; front-loaded with 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 Belgian income tax, the description specifies the tax year and output fields. With an output schema present, the description does not need to detail return values. Could mention assumptions (e.g., deductions), but overall adequate.

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

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

The input schema has 100% coverage with a description for 'income' ('Annual taxable income in euros'). The tool description adds no additional meaning beyond this, so baseline score of 3 is appropriate.

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

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

The description clearly states the verb 'Calculate', the resource 'Belgian personal income tax (IPP/PB)', and specifies 'using 2026 progressive brackets'. It distinguishes itself from sibling tax calculators by the country and acronym.

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 directs users to 'list_bundles' for related calculators, implying a context but not explicitly stating when to use this tool versus alternatives like other Belgian tax tools. No when-not or exclusion criteria are provided.

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

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

No annotations provided, so description carries full burden. States 'returns monthly pension estimate' but lacks details on limits, accuracy, or side effects. Discloses basic behavior but not comprehensive.

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?

Description is concise (5 sentences) and front-loads purpose. However, the final sentence about 'list_bundles' is tangential. Overall, it's efficient but slightly off-topic.

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 parameter count (3), schema coverage (100%), and output schema present, description should be comprehensive. However, the parameter mismatch is a critical gap. Also, output is vague ('monthly pension estimate') without details on calculation or return format.

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

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

Schema coverage is 100%, baseline 3, but description adds misleading info: says 'status (employee/self-employed)' while schema has 'household_type' with 'single'/'household'. This reduces value. Otherwise, explains inputs generally.

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?

Clearly states verb 'estimate', resource 'Belgian retirement pension', and inputs 'career years and average salary'. Distinguishes from siblings by specifying Belgian context and referencing 'finance-belgique' calculators.

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

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

Explicitly says 'Use for retirement planning in Belgium', but does not provide when-not-to-use or alternatives. Mention of 'list_bundles' is vague. There is a mismatch: description mentions 'status (employee/self-employed)' while schema uses 'household_type' with 'single'/'household'.

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 provides key behavioral context: it is an approximation, returns multiple net salary components, and uses Belgian rules. However, it does not disclose the tax year or assumptions, which would improve 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 two sentences, front-loading the purpose and then listing outputs and a reference. No wasted words.

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 single parameter and the output field listing, the description is largely complete. However, it could mention limitations (e.g., employee vs self-employed) or that rates are dynamic.

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

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

Schema coverage is 100% with parameter 'gross_monthly' described. The tool description does not add semantic meaning beyond the schema, so a baseline score of 3 is appropriate.

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

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

The description clearly states the tool converts Belgian gross monthly salary to net salary, using a specific verb ('Convert') and resource. It distinguishes itself from sibling tools like 'calculate_belgian_income_tax' by focusing on salary conversion and referencing a related bundle.

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 mentions 'See list_bundles for related finance-belgique calculators,' which hints at related tools but does not explicitly specify when to use this tool versus alternatives. It lacks exclusions or guidance on limitations.

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, and the description does not disclose behavioral traits such as being read-only, authentication needs, or side effects. The description relies on the tool name implying a calculation, but fails to explicitly confirm it is safe.

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

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

The description is concise with two sentences, but the first sentence is dense with return field names. It is not overly verbose and effectively communicates the tool's purpose.

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

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

For a simple one-parameter calculation tool with implied output schema, the description covers the function and return fields. It lacks mention of assumptions or limitations (e.g., legal context), but is mostly complete.

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

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

The input schema has 100% coverage for the single parameter, describing it as 'Annual net professional income in euros'. The description does not add further semantics beyond what the schema provides, meeting the baseline.

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 verb 'Calculate' and the resource 'Belgian self-employed social contributions (cotisations INASTI)', and lists specific return fields, making it distinct from sibling calculator 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 only mentions 'See list_bundles for related ''finance-belgique'' calculators', which implies context but does not explicitly specify when to use this tool vs alternatives or any prerequisites.

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

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

With no annotations, the description carries full burden but only states the conversion direction and output structure. Missing behavioral traits such as idempotency, error behavior, or whether it accepts negative amounts beyond schema constraints.

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

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

Two sentences with clear separation of purpose and return value. Efficient but could be improved by front-loading the conversion direction more explicitly (already does). No wasted words.

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 presence of an output schema (signaled), the description mentions the return object, which is helpful. However, it lacks guidelines and behavioral details. For a simple calculator with many siblings, it is minimally complete but not thorough.

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

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

Schema coverage is 100%, so baseline is 3. The description adds context about the return object, which indirectly relates to parameters, but does not enhance parameter meaning beyond what the schema already provides.

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

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

The description clearly states it calculates Belgian VAT and converts between HT and TTC, with a specific verb and resource. It distinguishes from siblings like calculate_vat_generic by specifying Belgian context and the return object format.

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?

No explicit guidance on when to use this tool versus alternatives. The reference to list_bundles is indirect and does not help an agent decide between similar VAT calculation tools (e.g., calculate_vat_generic, calculate_french_vat).

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?

Without annotations, the description explains the tool computes cycles and returns three values (-100 to +100) and a zone. It is a read-only calculation with no destructive behavior, and the disclosure is sufficient.

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

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

The description is concise with two sentences, front-loading the purpose and including key details without unnecessary words.

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

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

The description covers input, output format, and purpose. Given the simple nature of the tool and presence of an output schema, it is mostly complete, though edge cases like timezone or invalid dates are not addressed.

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

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

The input schema has 100% coverage for two parameters, both described as 'YYYY-MM-DD' strings. The description only reiterates the parameter names without adding new meaning, so baseline score is appropriate.

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

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

The description clearly states the tool computes physical, emotional, and intellectual biorhythm cycles for a date based on birth date. It also specifies the target audience (self-tracking enthusiasts) and distinguishes from siblings by referencing list_bundles for related fun calculators.

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

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

The description provides context for use (self-tracking, pseudoscience) and directs to list_bundles for similar tools, but does not explicitly state when not to use or compare with 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?

No annotations are provided, so the description carries the full burden. It mentions the formula and return fields but does not disclose assumptions, limitations, or edge cases of the Widmark formula.

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 two sentences, front-loaded with the verb 'estimate' and resource 'blood alcohol content', and includes all essential information without fluff.

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 presence of an output schema and 4 well-documented parameters, the description covers the essential context. It mentions the formula and return fields, though it could elaborate on use cases or assumptions.

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

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

Schema coverage is 100%, and descriptions for each parameter are already in the schema. The tool description adds little beyond mentioning the formula name and return format, so it does not significantly compensate.

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 estimates BAC using Widmark formula, specifies the return fields, and mentions related tools via list_bundles, effectively differentiating from siblings.

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

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

The description does not explicitly state when to use this tool versus alternatives like calculate_alcohol_units or calculate_bac_points. It references related tools but lacks exclusions or context for selection.

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

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

No annotations are provided, so the description carries the full burden. It only states what the tool calculates, with no disclosure of side effects, idempotency, permissions, or other behavioral traits.

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 very short and front-loaded, containing only two sentences with no extraneous information. Every sentence serves a purpose.

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

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

The tool has an output schema, so return values need not be explained. The description is minimal but sufficient for a simple calculation tool, though it could mention the output categories.

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

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

Schema description coverage is 100%, so the schema already documents both parameters adequately. The description adds no extra meaning beyond the schema, meeting the baseline.

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 it calculates BMI and weight category, specifying the verb and resource. However, it does not differentiate from sibling tools like calculate_bmr or calculate_body_fat, which is a minor gap.

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 hints at related calculators via list_bundles, but does not explicitly state when to use this tool versus alternatives. No exclusions or prerequisites are mentioned.

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

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

No annotations provided, so the description carries full burden. It discloses the equation and output format, which is useful but minimal. No mention of side effects, permissions, or constraints beyond the schema.

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

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

Two concise sentences with no unnecessary words. The purpose and a helpful pointer to related tools are 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 simple calculator with schema and output schema, the description is adequate but lacks a full explanation of the return format (e.g., exact structure) and limitations. It hints at output {bmr_kcal} but no detail.

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

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

Schema coverage is 100% with clear parameter descriptions (units, constraints, enum). The description adds no additional meaning beyond what the schema already provides, resulting in 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 calculates Basal Metabolic Rate using a specific equation (Mifflin-St Jeor) and mentions the return format. The name 'calculate_bmr' and sibling context (e.g., calculate_bmi, calculate_tdee) help differentiate it.

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?

No explicit guidance on when to use this tool versus alternatives. The description references 'list_bundles' for related calculators but does not provide comparative context or use cases.

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

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

With no annotations, the description carries full burden. It explains the calculation method (Deurenberg equation), input parameters, and output format. It does not disclose limitations or prerequisites beyond the schema, but for a simple calculator, it is fairly transparent.

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

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

The description is two sentences, front-loading the purpose and method. Every sentence provides necessary information without redundancy. It is highly concise and well-structured.

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

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

Given the presence of an output schema and three straightforward parameters, the description covers purpose, method, and output. It hints at related tools via list_bundles. It could mention validity or the equation's origin, but is largely complete for a calculator 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 100%, so the baseline is 3. The description adds minimal value by naming parameters in context but does not provide additional semantic details beyond the schema.

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

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

The description clearly states the tool's purpose: estimating body fat percentage from BMI, age, and sex using the Deurenberg equation. It also specifies the return format and distinguishes itself from siblings like calculate_body_fat_navy by naming the specific equation.

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 a vague reference to 'list_bundles for related calculators' but does not explicitly state when to use this tool versus alternatives like calculate_body_fat_navy. Usage guidance is implied but not direct.

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 does not disclose whether the tool is read-only or has side effects. However, the purpose implies a safe calculation, and no contradictions exist. It meets a minimum but lacks explicit safety or behavioral notes.

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

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

The description is a single sentence covering the core function and a helpful cross-reference. It is front-loaded and contains no unnecessary words.

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 presence of an output schema and the clear input schema, the description is largely complete. It does not explain the Navy method or assumptions, but the name and cross-reference provide sufficient context for a calculator 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 100%, so baseline is 3. The description adds no additional meaning beyond the schema's parameter descriptions. No parameter details are provided in the description.

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 body fat percentage using the US Navy circumference method, which distinguishes it from other body fat calculators among siblings. The verb+resource combination is specific and unambiguous.

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

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

The description provides no guidance on when to use this tool versus alternatives like calculate_body_fat. The mention of list_bundles for related calculators is vague and does not help an agent decide between tools.

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

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

No annotations provided, so description must carry behavioral disclosure. Only states basic conversion; no mention of side effects, precision, error handling, or limits beyond schema.

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

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

Two concise sentences. First delivers purpose, second provides a navigation hint. No verbosity.

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?

Simple tool with 2 well-described parameters and an output schema. However, missing example or explanation of output format. Adequate but not thorough.

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 covers both parameters (bpm range, note_value enum) with descriptions. Description adds no extra meaning beyond 'for different note values', which is already present. Baseline 3.

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?

Clearly states the conversion from BPM to milliseconds for note values. However, it does not differentiate from siblings beyond pointing to a bundle for related calculators.

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

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

Minimal guidance: only says to see 'list_bundles' for related calculators. No explicit when to use or not use this tool 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 carries the full burden. It states the tool computes distances (a read/calculation operation), but does not disclose any behavioral constraints like rate limits, data requirements, or side effects. The description adds minimal extra value beyond the tool's name.

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

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

The description is concise with four sentences, each adding value: purpose, usage, inputs, and a cross-reference. It front-loads the key action. However, the inclusion of an incorrect parameter reduces efficiency, costing a point.

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 low complexity, full schema coverage, and presence of an output schema, the description provides adequate overall context. However, the erroneous mention of 'reaction time' creates confusion and undermines completeness.

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?

Although the input schema covers 100% of parameters, the description incorrectly lists 'reaction time s' as an input, which is not in the schema. This misleads the agent into expecting a parameter that doesn't exist, reducing the usefulness of the description. The schema already sufficiently describes speed_kmh and condition.

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

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

The description clearly states the tool computes reaction and braking distance based on road condition, using specific verbs like 'Compute' and identifying the resource ('braking distance'). It distinguishes from sibling tools by mentioning 'driver safety education' and pointing to the bundle 'auto-transport' for related calculators.

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

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

The description explicitly recommends use for driver safety education and directs users to list_bundles for related calculators. However, it does not explicitly state when not to use this tool or alternative tools, which is acceptable given the tool's simplicity but slightly limits guidance.

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

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

No annotations provided, so description carries full burden. It explains the calculation and return values (ratio and meters per pedal turn), but does not mention any permissions, side effects, or the fact that one mentioned parameter is not in the schema.

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

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

The description is concise with two sentences, each serving a purpose: defining the computation and providing usage context. The mention of a non-existent parameter slightly detracts from efficiency.

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

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

Given the tool has an output schema, the description adequately mentions return values. However, the inclusion of a non-existent input parameter makes the description incomplete and potentially misleading.

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

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

Schema description coverage is 100% with both parameters having descriptions. However, the description introduces 'wheel diameter mm' as an input that is not in the schema, creating inconsistency and reducing clarity rather than adding value.

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 that the tool computes cycling gear ratio and development, specifying inputs and outputs. However, it mentions 'wheel diameter mm' as an input that is not present in the schema, which could cause confusion.

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 says 'Use for road cycling gear analysis' and suggests related calculators in 'list_bundles', providing some context but no explicit guidance on when not to use or alternatives 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?

No annotations are provided, so the description must carry the full transparency burden. It discloses the calculation inputs and outputs, but does not mention edge cases, error behavior, or any side effects. For a simple calculator, this is adequate but not thorough.

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 extremely concise, consisting of two short sentences. The first sentence immediately states the purpose and required inputs, and the second sentence provides a useful pointer to related tools. No unnecessary words.

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 simplicity of the tool and the presence of an output schema (implied by the return format in the description), the description provides sufficient context. It covers purpose, inputs, outputs, and a reference to related tools. Minor omission: no mention of measurement unit constraints or validation.

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%, meaning the input schema lacks descriptions. The description mentions 'underbust and bust measurements (cm) and system' but does not explain each parameter in detail (e.g., what 'underbust' means). The parameter names are self-explanatory, but the description could add more value.

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 bra size in FR, US, or UK systems from underbust and bust measurements (cm), and specifies the return format. It distinguishes itself from the sibling 'calculate_bra_size_convert' by focusing on calculation rather than conversion.

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 mentions the input measurements and systems, and directs users to 'list_bundles' for related calculators. It does not provide explicit when-not-to-use advice, but the context is clear enough for a straightforward calculation tool.

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

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

No annotations are provided, so the description must disclose behavioral aspects. It states the output format ({FR, US, UK, EU}) but does not explicitly confirm it is a read-only operation or mention any side effects, rate limits, or error handling.

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 extremely concise with two sentences, front-loading the core purpose and output format. Every sentence serves a purpose with no unnecessary words.

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

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

For a simple conversion tool with 3 parameters and an indicated output schema, the description covers the essential functionality. However, it could be improved by noting that cup size mappings may vary per system or referencing the sibling tool for further 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?

All three parameters have descriptions in the schema (100% coverage), and the description does not add additional semantic detail beyond what is already in the schema. The baseline of 3 is appropriate.

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

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

The description clearly states the tool converts bra sizes between FR, US, UK, and EU systems. The verb 'convert' and resource 'bra size' are specific, and the scope across four systems distinguishes it from the sibling 'calculate_bra_size'.

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 mentions 'See list_bundles for related calculators' but does not explicitly state when to use this tool versus alternatives or when not to use it. It implies conversion use but lacks clear exclusion criteria.

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

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

No annotations are provided, so the description fully discloses behavior: it computes hydration percentage and returns dough type. Since it is a simple calculation, no side effects or destructive actions exist. The description is transparent about what it does.

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 extremely concise, with two sentences plus a formula. It front-loads the purpose and includes the formula, input summary, output summary, and a pointer to related tools. Every sentence is valuable and no extraneous content.

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

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

For a simple two-parameter calculation tool with an output schema, the description covers all needed aspects: purpose, formula, inputs, outputs, and even a reference to related tools. No gaps remain.

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

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

Input schema has 100% description coverage, so the baseline is 3. The description adds 'Inputs: flour g, water g' and the formula, which reinforces parameter meaning but does not add significant new information beyond the schema.

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

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

The description provides the exact formula and explicitly states it computes baker's hydration percentage for bread recipe analysis. The verb 'compute' and the formula make the purpose clear and distinguishable from the many sibling calculate_* 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 advises 'Use for bread recipe analysis,' which gives clear context. It also points to list_bundles for related calculators, implying alternatives. However, it does not explicitly state when not to use this tool, but the context is sufficient.

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 burden of behavioral disclosure. It states the tool computes and returns values, implying read-only behavior, but does not explicitly confirm no side effects, destructive actions, or other traits. The description is adequate but not rich in behavioral 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 three sentences long, each serving a distinct purpose: stating the function, providing usage context, listing inputs and outputs, and directing to related tools. There is no fluff, and it is efficiently 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?

The description adequately covers the tool's purpose, inputs, and outputs. It does not detail edge cases (e.g., what if price_per_unit equals or is less than variable_cost_per_unit), but given the presence of an output schema and the tool's straightforward nature, the description is sufficiently complete.

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

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

The input schema has 100% coverage with clear descriptions for each parameter. The description lists the inputs ('fixed costs, price/unit, variable cost/unit') but adds no additional meaning beyond what the schema already provides, meeting the baseline for full coverage.

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 starts with 'Compute break-even point in units and revenue,' which specifies the verb and the resource. It also distinguishes from sibling tools by mentioning related 'finance-universal' calculators, making its exact purpose unambiguous.

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

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

The description provides a usage context ('Use for business plans and pricing decisions') but does not explicitly state when not to use this tool or contrast it with specific alternatives like calculate_profit_margin. The reference to list_bundles is helpful but lacks direct exclusion.

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

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

No annotations are provided, so the description carries full burden. It states 'Returns due date and gestation milestones' but provides no details on the format, number of milestones, or any side effects. The species mismatch further reduces 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 concise, with one sentence and a simple listing of inputs and returns. It avoids unnecessary fluff, though the species list could be aligned to schema.

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 that an output schema exists, the description's mention of gestation milestones is adequate but incomplete due to the species discrepancy and lack of detail on available species. The tool's role among many sibling pregnancy calculators is not fully clarified.

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 lists species but includes horse/cow, which are not in the schema (which has hamster instead). This misrepresentation adds confusion rather than clarity. No additional constraints on mating_date format are given.

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 it computes a due date for animal breeding, targeting breeders. However, it lists species (horse/cow) that do not match the schema enum (dog/cat/rabbit/hamster), creating potential confusion for the agent.

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 mentions 'Use for breeders' and directs to list_bundles for related calculators, implying some context but lacks explicit guidance on when to prefer this tool over species-specific pregnancy calculators (e.g., calculate_dog_pregnancy) or 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?

No annotations are provided, so the description carries the full burden. It mentions 'Estimate' and 'Returns total points and mention' but does not disclose that the tool is read-only, idempotent, or has no side effects. For a calculation tool, this is a notable gap in 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 three sentences: purpose, usage scope, inputs/outputs, and a pointer to related tools. Every sentence serves a purpose, and key information is front-loaded. No unnecessary words.

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

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

Given the tool has 6 required parameters and an output schema, the description adequately explains the domain (French Brevet) and what the tool does. It mentions output types ('total points and mention'). It could be slightly improved by noting that the calculation follows official formula, but it is sufficient for a calculator 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 coverage is 100% with each parameter having a description. The description adds only general context ('grades by subject, continuous control') but does not explain calculation specifics or how parameters relate to each other. Thus, it adds marginal value beyond the schema, earning a baseline 3.

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: 'Estimate French Brevet (DNB) score from grades and continuous-control marks.' It specifies the target users ('collège students') and what it returns ('total points and mention'). This distinguishes it from siblings like calculate_bac_points, which handles a different exam.

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 says 'Use for collège students forecasting their result' and points to list_bundles for related education calculators. However, it does not explicitly state when not to use it or contrast with alternatives like calculate_bac_points. The context is clear but lacks explicit exclusions.

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?

The description states it includes waste margin and returns brick count and pallets, but it references inputs (brick size, waste %) that are not present in the input schema. This discrepancy harms transparency. Without annotations, it carries the full burden but is partially accurate.

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 short and front-loaded with the main purpose. However, it includes extraneous input mentions that are not supported, which slightly detracts from its conciseness. Overall, it is efficient but could be more accurate.

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 simplicity of the tool (3 parameters, output schema exists), the description should fully cover behavior. It mentions output but fails to describe the type parameter or align with the schema. The waste margin claim is unsubstantiated. This incompleteness reduces its utility.

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

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

Schema coverage is 100%, so baseline is 3, but the description adds misleading information by mentioning 'brick size' and 'waste %' which are not in the schema. This contradicts the schema and reduces clarity. The description should align with the defined parameters.

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

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

The description clearly states the tool computes bricks or blocks needed for a wall, including waste margin, and references a related tool for more calculators. It specifies the domain (masonry projects) and the main objective, though it could better differentiate from other calculate_* tools.

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

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

The description explicitly says 'Use for masonry projects' and directs to list_bundles for related calculators, providing some usage context. However, it does not mention when not to use this tool or provide alternatives beyond the bundle tool.

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

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

No annotations are provided, so the description must disclose behavior. It states the tool computes and returns results, implying read-only behavior. However, it does not discuss edge cases, error handling, or any state changes. For a straightforward physics calculator, this is adequate but not thorough.

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

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

The description is concise at two sentences plus a reference, with no unnecessary words. It front-loads the core purpose and then adds usage context. While it could be more structured (e.g., listing outputs explicitly), it earns its length.

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 simplicity (3 parameters, 2 required, output schema present), the description covers the essential aspects: what it computes, inputs, outputs, and general usage domain. It is complete enough for an agent 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?

The input schema has 100% description coverage, with each parameter having a clear description (e.g., 'Object volume m³', 'Fluid density kg/m³'). The description adds 'Inputs: object mass/volume, fluid density' but does not provide additional meaning beyond what the schema already offers.

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

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

The description clearly states the tool computes buoyancy force, displaced volume, or floating analysis using Archimedes principle. It specifies usage for physics or shipping and mentions outputs (buoyant force, float/sink verdict). The reference to 'science' calculators in list_bundles helps differentiate from siblings.

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

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

The description suggests using the tool for physics or shipping but does not provide explicit guidance on when not to use it or direct alternatives. The mention of list_bundles for related calculators is vague and doesn't name specific sibling tools that might be more appropriate in certain 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?

No annotations are provided, so the description must cover behavioral aspects. It explains the computation (returns burn, runway, profitability date) and required inputs, but does not disclose any side effects, limits, or performance characteristics. Basic transparency is achieved.

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 three sentences with no filler. It front-loads the primary action and quickly covers inputs, outputs, and a pointer to related tools. Every sentence serves a purpose.

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 simplicity (3 parameters, no nested objects) and the presence of an output schema, the description sufficiently covers purpose, usage, inputs, and outputs. It also references a related bundle, adding completeness.

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

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

The input schema has 100% description coverage, providing baseline semantic detail. The description reiterates input names (cash on hand, monthly expenses, monthly revenue) but does not add new meaning beyond the schema. Output description adds some context.

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

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

The description clearly states the tool computes startup monthly burn rate and runway, listing inputs and outputs. It mentions a related bundle, but does not explicitly differentiate from sibling financial calculators like calculate_churn_rate.

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 specifies use cases: 'Use for fundraising or expense control.' It also directs users to 'list_bundles' for related calculators, but lacks explicit when-not-to-use guidance.

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

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

With no annotations, the description should disclose behavioral traits. It only mentions returns, omitting details on side effects, permissions, or limitations (e.g., voltage validation).

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

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

Three succinct sentences, front-loaded with purpose, then usage, then related tool. No unnecessary words.

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?

Adequate for a calculation tool with output schema, but lacks details on output format, rounding, or standard applicability (e.g., only French code).

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 descriptions cover all parameters, but the description incorrectly states 'power kW' while the parameter is 'power_w' (watts), creating potential confusion.

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?

Clearly states it computes cable cross-section per NF C 15-100 for residential wiring, distinguishing it from generic cable calculators or the sibling 'calculate_cable_section_electrical'.

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

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

States 'Use for residential wiring' and references related calculators, but does not explicitly specify when not to use or advise 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 must disclose behavioral traits. It reports the input parameters and output shape, but omits important assumptions (e.g., single-phase vs. three-phase, conductor material, temperature). It does not state that the calculation is read-only or whether it has side effects, though this is typical for a calculation tool. The description adds some value beyond the schema but lacks key 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 two sentences long, with the first sentence stating the purpose and inputs, and the second listing the output structure and a pointer to list_bundles. It is front-loaded, efficient, and contains no unnecessary words.

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

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

For a calculation tool with 4 parameters (2 required) and an output schema, the description is adequate but not thorough. It covers inputs and output shape but lacks details on underlying formulas, assumptions (e.g., conductor material, power factor), or typical usage scenarios. The output schema exists but is not described in full; the description gives keys but not units or interpretation. Some gaps remain for an AI agent to use without additional context.

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

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

Schema description coverage is 100%, meaning all parameters already have individual descriptions. The description merely summarizes these inputs without adding new meaning or clarifying edge cases (e.g., units for power_w). Therefore, it does not significantly enhance understanding beyond the schema.

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

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

The description clearly states 'Calculate cable section from power, voltage, distance and max voltage drop,' which is a specific verb+resource. It also lists the return structure, leaving no ambiguity about what the tool does. The mention of list_bundles indirectly distinguishes it from related calculators, though not from the sibling 'calculate_cable_section' directly.

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 no explicit guidance on when to use this tool versus alternatives like 'calculate_cable_section'. It does not specify prerequisites, conditions for use, or when not to use it. The reference to list_bundles is vague and does not constitute clear usage guidelines.

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

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

No annotations provided, so description carries full burden. Discloses inputs (CAC, LTV) and outputs (ratio, health verdict). As a calculation tool, no side effects expected, and description adequately conveys behavior.

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

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

Two sentences, no wasted words. Front-loaded with purpose, uses, and pointers. Excellent 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?

Output schema exists so return values are covered. Description mentions ratio and health verdict, sufficient for a simple calculation tool. Complete given context signals.

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

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

Input schema has 100% coverage with descriptions (EUR denominations). Description repeats 'total CAC, LTV' without adding new meaning. Baseline 3 given high schema coverage.

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?

Clear verb 'Compute' and specific resource 'CAC vs LTV ratio' with context of SaaS unit economics. Distinguishes from siblings via reference to list_bundles for related calculators.

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

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

Explicitly states use case ('SaaS unit economics analysis') and target ratio (≥3.0). Provides pointer to related calculators via list_bundles. Lacks explicit when-not-to-use or alternative tools.

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

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

No annotations provided, so the description carries the full burden. It discloses the half-life assumption (5-hour) which is a specific behavioral trait. However, it does not mention any other behavioral aspects like external dependencies or mutation potential, but for a calculator, this is minimally acceptable.

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 three sentences with no redundant information. It front-loads the core action, then provides usage context, and finally mentions return and related tools. Every sentence adds value.

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

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

For a simple calculator with two parameters and an output schema (implied), the description covers what it does, how to use it, what it returns, and where to find related tools. No critical gaps for execution.

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

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

Schema coverage is 100%, so baseline is 3. The description paraphrases the parameters ('caffeine mg, time since intake') but does not add new meaning beyond the schema descriptions. No additional units, constraints, or examples.

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 verb 'Compute', the resource 'caffeine in body', and the scope 'over time using 5-hour half-life'. It distinguishes from siblings like calculate_caffeine_half_life and calculate_caffeine_intake by focusing on remaining caffeine for sleep planning.

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

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

The description explicitly says 'Use for sleep planning', providing clear context. It also mentions 'See list_bundles for related sante calculators', which hints at alternatives but does not explicitly exclude other tools or state when not to use.

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

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

No annotations provided, so the description must carry the full burden. It mentions return fields but does not disclose whether it is read-only, idempotent, or requires any state. As a calculation, behavior is somewhat implied, but explicit transparency is lacking.

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

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

Two sentences with no fluff. The first sentence states the action, the second provides return format and a pointer to related tools. Front-loaded and every sentence earns 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?

For a simple calculation tool, the description includes return fields and notes related tools. The input schema covers parameters. However, it does not mention the half-life assumption (e.g., 5 hours) which could be important for accuracy, but overall the context is adequate.

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

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

Schema description coverage is 100%, baseline applied. The description adds no additional meaning to the parameters beyond what the schema already provides, so it does not improve parameter understanding.

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 it calculates remaining caffeine after time, with a specific verb and resource. It distinguishes itself from siblings by being a caffeine half-life calculator, but could be more precise by mentioning the half-life concept.

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?

No explicit guidance on when to use this tool versus sibling calculators such as calculate_caffeine_clearance or calculate_caffeine_intake. The mention of 'list_bundles' hints at context but does not provide usage criteria or exclusions.

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

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

No annotations provided, so description carries full burden. Clearly states inputs and outputs (total mg, % limit, distribution), implying a read-only calculation tool. No contradictions.

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

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

Three concise sentences covering purpose, usage, inputs, outputs, and related tools. No wasted words, 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 many sibling calculators, description fully covers purpose, inputs, outputs, and links to relevant bundles. Output schema would fill remaining detail.

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