MaCalculatriceEnLigne

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

With no annotations, the description carries full burden. It discloses the formula used (Epley) and the output structure (input_weight, input_reps, estimated_1rm). However, it does not mention limitations, assumptions, or edge cases such as the formula's accuracy for high reps or invalid inputs 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, no filler. The first sentence defines the core functionality and formula; the second describes the output and points to related tools. Every word 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?

Given the existence of an output schema (which likely defines the table format) and the modest complexity of generating a rep table, the description is nearly complete. It lacks explicit detail on the table range (1-12 reps assumed) and step size, but the output schema likely covers that.

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 by stating 'from a known lift' and listing the output fields, which reinforces the usage intent but does not provide additional parameter meaning beyond the schema's inline 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 the tool generates a 'full 1RM-to-12RM repetition table' using the 'Epley formula', distinguishing it from the sibling 'calculate_one_rep_max' which likely provides only a single estimated 1RM. The verb 'generate' and specific resource 'repetition table' are precise.

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 using this tool when a full table of estimated 1RM for multiple reps is needed, as opposed to the singleton sibling. It also directs users to 'list_bundles' for related calculators. However, explicit when-not-to-use or alternative selection criteria are absent.

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 does not disclose error handling, edge cases (e.g., minutes >60 carryover), or validation behavior beyond schema. 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 is concise, front-loaded with the core action, and includes a useful pointer to related tools. 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 existence of an output schema and the simplicity of the tool, the description is mostly complete. It could mention minute carryover behavior, but overall it's 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 100%, so the baseline is 3. The description adds no additional meaning beyond the schema's parameter descriptions (e.g., 'First duration — hours').

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 action 'Add two time durations' and the output 'return the total in hours and minutes'. It references list_bundles for related tools, distinguishing it within the calculator family.

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

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

The description provides clear context for usage, but lacks explicit guidance on when not to use it or comparison with sibling tools beyond the reference to list_bundles. For a simple addition tool, this is adequate.

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

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

With no annotations provided, the description carries the full burden and lists all output fields (today, age_years, age_months, age_days, total_days_lived, days_to_next_birthday), detailing what the tool returns. It does not mention side effects or authorization, but for a calculation tool, this is reasonably 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 with no fluff. The first sentence succinctly conveys purpose and output, and the second provides a helpful reference to related calculators. It is well-structured and efficiently uses space.

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 (one parameter, output schema embedded in description), the description covers input and output well. It lacks mention of error conditions (e.g., invalid future dates) but is otherwise complete for the intended use.

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% for the single parameter birth_date, which already specifies format YYYY-MM-DD. The description adds no additional meaning beyond stating the tool uses a birth date, so baseline 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, using a specific verb and resource. It differentiates from siblings like calculate_age_in_units by specifying the output components, though it does not explicitly contrast.

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

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

The description implies usage for calculating age from a birth date but provides no guidance on when not to use this tool or alternatives. The mention of list_bundles for related calculators is vague and does not offer clear exclusions or context for selection among many sibling 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 are provided, so the description must disclose behavior. It states it returns age in weeks, hours, minutes, seconds, but does not clarify whether it also includes years, months, days, or how edge cases like leap years or time zones are handled. The claim of 'exact age' is somewhat vague.

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 primary purpose. It avoids unnecessary words but could be more informative about the return structure. Still, it is 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?

Given the tool's simplicity (one parameter, no nested objects) and the existence of an output schema, the description provides adequate context. It explains the main function and return keys, though it omits details like whether years are included. Given the output schema fills gaps, this is 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?

The schema covers 100% of parameters with a single 'birth_date' described as 'Birth date YYYY-MM-DD'. The description only adds 'from birth date', which adds minimal meaning beyond the schema. Baseline is 3 due to 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?

The description clearly states the tool's purpose: 'Calculate exact age in multiple units from birth date.' It specifies the return values (weeks, hours, minutes, seconds), distinguishing it from sibling tools like 'calculate_age' which likely returns years only.

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

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

The description mentions 'See list_bundles for related 'fun' calculators,' offering a pointer to related tools but does not explicitly state when to use this tool versus its sibling 'calculate_age' or others. It lacks precise when-to-use and 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?

No annotations provided, so description carries full burden. It describes inputs and outputs but does not disclose any behavioral traits such as permissions, side effects, or error handling. It is not contradictory but could be more informative.

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 relatively concise with a clear front-loaded purpose and a note about related tools. It could be slightly more efficient, but it is 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 (though not shown), the description adequately lists return values. However, it misses describing the input structure (array of drink objects) and the required type field, which is a significant gap.

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 volume and ABV, which are key inputs, but omits the required 'type' field. With 0% schema coverage, the description should compensate but is incomplete, missing important context about the drink type enumeration.

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 alcohol units (UK) and grams of pure alcohol for a drink, with a specific use case for health tracking and limit awareness. Distinguishes from siblings by mentioning UK units and standard-drink equivalent, and points 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?

Provides a use case for health tracking and limit awareness, but lacks explicit guidance on when not to use this tool versus similar tools like calculate_blood_alcohol. The mention of list_bundles hints at alternatives but is not explicit.

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 traits. It only states the operation and output fields, without disclosing any side effects, dependencies, or constraints beyond what the input schema provides. The description adds minimal behavioral 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 extremely concise: two sentences that front-load the purpose and list the return fields. 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 simple calculator with one parameter and an output schema, the description covers the basic purpose and output. However, it lacks usage guidance and behavioral transparency, which are needed given the absence of annotations.

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% for the single parameter 'altitude_m', which is well-documented in the schema. The description does not add significant meaning beyond the schema, meeting the baseline for high 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 the tool's function: 'Assess altitude sickness risk and recommend acclimatization schedule.' It specifies the return format, distinguishing it from sibling calculators. Mentioning list_bundles for related voyage calculators provides context.

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 when needing altitude sickness risk assessment, but it does not explicitly state when to use this tool versus alternatives. The reference to list_bundles for voyage calculators offers some guidance, but lacks direct usage context.

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 behavioral burden. It only states basic conversion and mentions 'Returns: {original}', which is unclear. No disclosure of requirements, side effects, or limitations.

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

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

The description is very concise with one sentence and a reference. However, the 'Returns: {original}' placeholder is puzzling and slightly reduces clarity.

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

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

Given the simplicity of the tool and the existence of an output schema (as per context), the description is largely complete. It could be improved by distinguishing from the sibling 'convert_angle'.

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 parameters are fully described in the schema. The description adds no additional meaning beyond listing the units, which are already in the enum definitions.

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

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

The description clearly states the tool converts angles between degrees, radians, gradians, and turns. However, it does not differentiate from the sibling tool 'convert_angle', which likely has a similar 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 provides minimal guidance, only referencing 'list_bundles' for related calculators. It does not explicitly state when to use this tool versus alternatives like 'convert_angle'.

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 object structure, but lacks information about side effects, safety (e.g., read-only nature), 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?

Two concise sentences: first states purpose, second lists returns and bundle reference. No wasted words, but could be structured with bullet points for readability.

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

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

With no annotations, the description covers basic purpose and returns but omits edge cases (e.g., zero rate), validation rules, or error scenarios. Adequate for a straightforward 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?

Schema coverage is 100% with clear descriptions. The description adds no extra meaning beyond the schema, such as unit clarification or parameter interdependencies.

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 periodic payment for a loan or annuity and lists return fields. It references related calculators via list_bundles but does not explicitly differentiate from siblings like calculate_loan_payment.

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 mention of 'related finance-universal calculators' is vague and does not provide situation-specific advice.

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

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

With no annotations provided, the description carries full burden. It mentions 'AI-powered' and 'requires premium subscription', but does not disclose whether the tool is read-only, destructive, rate-limited, or how it handles errors. Minimal behavioral context beyond subscription requirement.

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, front-loaded with key information (universal nature and subscription requirement). 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's role as a fallback calculator and the existence of an output schema, the description covers the essential purpose and a constraint. It could mention potential limitations or error handling, but it's sufficiently complete for an agent to understand when to use it.

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 input schema already explains the two parameters (query and context) well. The description adds no additional meaning to the parameters, achieving the 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?

Explicitly states it's a universal calculator for any calculation not covered by specialized tools, clearly distinguishing from the vast list of sibling tools that cover specific domains.

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?

Clearly indicates when to use (for calculations not covered by specialized tools) and includes a prerequisite (requires premium subscription). Does not explicitly name alternatives, but the purpose implies using specialized tools first.

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 mentions output (liters and gallons) but inaccurately describes inputs (shape options like radius) that mismatch the schema. It also fails to disclose the optional substrate parameter, leaving behavior under-specified.

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 relatively short and front-loaded with the core purpose. However, the inaccurate input description consumes space without adding value, reducing overall 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?

The tool has an output schema (not provided), so return value detail is not required. But the description omits the substrate parameter entirely, and the input description is incorrect. For a 4-parameter tool with 0% schema coverage, this is 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?

Schema description coverage is 0%, so the description must explain parameters. It does not list or explain length_cm, width_cm, height_cm, or substrate_cm individually. The general input description is inconsistent with the schema, adding no useful meaning.

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 the tool computes aquarium water volume in L and US gallons, which is clear. However, it mentions shape options (rectangular/cylindrical/bow-front) that are not reflected in the input schema, which only has length, width, and height. This inconsistency undermines clarity.

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 usage contexts ('Use for fishkeeping, dosing, and stocking decisions') and directs to list_bundles for related calculators. It does not explicitly state when not to use, but the guidance is sufficient for typical 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 provided, so description carries full burden. It discloses input and output nature but lacks details on error handling, units validation, or behavior for missing/unexpected combinations of dimensions.

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 (3 sentences) and front-loaded with purpose. The final sentence on related tools could be integrated, but overall efficient and clear.

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 and schema coverage, the description covers purpose, usage, and output. It might be slightly incomplete on specific parameter dependencies, but remains adequate for a math 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% coverage, so baseline is 3. Description adds only 'shape + dimensions' without mapping which parameters apply to which shapes, thus providing limited extra 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 clearly states 'Compute area for common 2D shapes,' listing example shapes and distinguishing from siblings like calculate_perimeter or calculate_volume. The verb+resource is specific and immediately understandable.

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 use cases (geometry, real estate, paint estimates) and suggests list_bundles for related calculators, but does not explicitly state when not to use or how it differs from similar tools like calculate_anything.

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

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

No annotations are provided, so the description carries the full burden. It discloses the tool is a calculator and lists output fields, implying it is a read-only computation. However, it does not mention any side effects or limitations beyond the scope of calculation.

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

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

The description is two sentences: the first states purpose and return fields, the second points to related tools. It is front-loaded and every sentence adds value with 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 complexity of French tax calculations, the description lists key return fields, and the schema covers parameters. The pointer to 'list_bundles' provides additional context. A brief explanation of terms like 'net_before_tax' could improve completeness, but it is still sufficient.

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

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

Schema coverage is 100% with descriptions for both parameters. The description does not add additional meaning beyond what the schema provides, 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?

Description explicitly states it calculates net income and social charges for French auto-entrepreneur, with a specific verb and resource. It lists return fields, clearly differentiating it from the many sibling calculator tools by targeting a specific regime.

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 clearly indicates this tool is for French auto-entrepreneur calculations and directs users to 'list_bundles' for related calculators. It provides context for when to use it, though it does not explicitly state 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, so description must disclose behavior. It lists mean types but doesn't explain how to select them (mode parameter missing from schema). No info on error handling, weight constraints, or return structure.

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, front-loaded purpose, includes reference to related tools. Efficient use of 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's complexity (multiple mean types) and no annotations, description is incomplete. Missing parameter details (mode) and output structure. Agent lacks info to use correctly 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 has 100% description coverage for both parameters, so baseline is 3. Description adds 'mode' mention but it's not in schema, reducing clarity. Doesn't enhance understanding 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?

Description clearly states compute different means and gives use cases. However, it mentions a 'mode' parameter not in schema, causing slight 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?

Specifies typical use cases (grade averages, returns, rates) and directs to list_bundles for related calculators. Lacks explicit when-not-to-use or 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?

Without annotations, the description carries full burden. It states inputs and output (weighted average and mention) but does not disclose the specific computation method, assumptions, or whether it handles all bac types. The schema provides coefficients but the description could add context on the formula logic.

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 with no wasted words. The first sentence establishes purpose, the second provides usage context, and the third summarizes inputs and outputs.

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

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

With an output schema present, the description sufficiently covers return values (weighted average and mention). It also references related calculators via list_bundles. Missing details like bac type coverage or mention thresholds, but the output schema likely fills gaps.

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 detailed parameter descriptions. The description adds minimal value beyond 'grades by subject with coefficients'. It does not clarify the unique 'continuous_control' scale (720) beyond what the schema captures.

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 estimates 'French Baccalauréat final score' and distinguishes it from the many other calculate_* tools by specifying the unique subject matter. The verb 'Estimate' and the context 'track lycée results' make the purpose specific and actionable.

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 tells when to use it ('track lycée results before official scores') and hints at alternatives by pointing to 'list_bundles' for related calculators. However, it does not explicitly state when not to use this tool or compare it to similar sibling tools like 'calculate_brevet_points'.

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 exist, so the description bears the full burden. It discloses that the tool reduces leavening, increases liquid, and raises temperature, and returns an adjusted recipe. This is sufficient for a simple calculator, though it lacks details on the algorithm or edge cases.

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

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

The description is two short sentences, front-loaded with the core purpose ('Adjust baking recipe for high altitude'), and contains no redundant information. Every part 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 recipe adjustment tool, the description covers what it does, when to use it, and the inputs/outputs. The presence of an output schema (not shown) alleviates the need to explain return values. Minor gaps include no mention of units (e.g., meters for altitude) but schema covers that.

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 all five parameters described in the schema. The description merely mentions 'altitude m, ingredients' without adding new meaning beyond the schema, which already provides parameter names, types, and 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 adjusts baking recipes for high altitude, specifying the resource (baking recipe) and the context (high altitude, mountain cooking). It is distinct from siblings like calculate_altitude_sickness or calculate_baking_conversion, though it does not explicitly differentiate itself.

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 mountain cooking' and references list_bundles for related cuisine calculators, providing basic usage context. However, it does not specify when not to use this tool or mention alternatives, leaving some ambiguity among the many calculate_* 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?

Without annotations, the description must disclose behavior. It states the conversion action and return of converted quantity, but the input mismatch reduces clarity. It does not mention idempotency or other traits, but for a calculator 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 short (two sentences plus note) but contains inaccurate information about inputs. It would be better to be accurate and concise.

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

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

Given there is an output schema, the description should clarify the limited input (cups only). It fails to do so, leaving the agent with mismatched expectations. For a simple calculator, basic completeness is missing.

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

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

Schema coverage is 0%, and the description adds incorrect parameter information (from-unit, to-unit) that conflicts with the actual schema (only ingredient and quantity_cups). This misleads the agent about required inputs.

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 baking measurements between cups, tablespoons, grams, and milliliters for common ingredients. It distinguishes from general cooking converters and sibling tools like convert_cooking and calculate_cooking_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 suggests using it for translating recipes across regions and directs to list_bundles for related calculators. However, it fails to clarify when not to use it, and the listed inputs (value, from-unit, to-unit) contradict the actual schema, which only accepts quantity_cups. This can mislead the agent.

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

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

With no annotations provided, the description carries the full burden. It discloses the return format ({input, decimal_value, result}), which adds value. However, it does not mention any behavioral traits such as error handling, input validation, or whether the operation is destructive or requires permissions. It is adequate but not fully transparent.

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

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

The description is very concise: one sentence describing the operation, a brief return format note, and a reference to related tools. Every part is necessary and there is no wasted text. It is front-loaded with the core 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 moderate complexity, the description covers the essential aspects: purpose, supported bases, and return values. The schema covers parameters thoroughly, and an output schema exists (though not shown here). It could be improved by mentioning valid input formats or edge cases, but for a calculator tool, it is substantially 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 description coverage is 100%, so the input schema already contains descriptions for all three parameters (value, from_base, to_base). The description adds no additional semantic meaning beyond what is in the schema. Baseline score of 3 is appropriate as the description does not go 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 numbers between bases (binary, octal, decimal, hexadecimal, any base 2-36). It uses a specific verb ('convert') and resource ('numbers between bases'), and explicitly lists example bases. The tool name also matches this purpose, and it is easily distinguished from the many sibling tools like convert_temperature or calculate_percentage.

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 implicit guidance by stating what the tool does, but it does not explicitly say when to use it versus alternatives. The reference to 'See list_bundles for related 'math' calculators' is somewhat helpful but does not directly contrast with sibling tools. No 'when-not-to-use' or exclusions 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; description lists return fields but does not disclose behavioral traits like side effects, permissions, or assumptions (e.g., beam theory, safety factors). Carries full burden but is minimal.

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 wasted words. Front-loaded with purpose and output summary.

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 simple tool with 3 parameters and an output schema, the description is almost complete. Could mention underlying assumptions or common units, but still sufficient for an agent to invoke correctly.

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

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

Schema description coverage is 100%, so baseline 3 applies. Description adds no additional parameter context beyond the schema, which already documents all three parameters adequately.

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 clearly states verb 'calculate' and resources 'max bending moment and shear for a beam under uniform distributed load'. It specifies outputs but does not differentiate from sibling tools beyond a generic reference to 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?

Description implies usage for beam load calculations and references list_bundles for related construction calculators, but lacks explicit when-to-use, when-not-to-use, or alternative tool 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 full responsibility. It lists return fields but does not disclose whether the tool is read-only, requires authentication, or has rate limits. Behavioral traits beyond return format are absent.

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

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

Two sentences with clear front-loading of purpose. The return field list may be redundant given the output schema, but the description is efficient and not verbose.

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

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

The description covers purpose and return fields, but lacks usage guidance and behavioral transparency. It is adequate for a calculator tool with output schema, but 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?

Schema description coverage is 100%, so each parameter is already documented. The description adds nothing about parameters beyond the schema. Baseline of 3 is appropriate.

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

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

The description states the specific verb 'Calculate' and resource 'Belgian benefit-in-kind for company car', with return fields. It distinguishes from siblings by mentioning related calculators in 'list_bundles', but does not explicitly differentiate from the many 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 does not specify when to use this tool versus alternatives. It only indirectly suggests related calculators via 'See list_bundles', but no explicit when/when-not guidance.

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

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

No annotations are provided, so the description carries full burden. It mentions outputs (tax due and effective rate) but does not disclose behavioral traits such as reliance on current tax law, rate updates, or limitations (e.g., integer amounts). Adequate but minimal.

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 purpose and use case, and efficiently conveys inputs, outputs, and a related tool. 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?

While an output schema exists, the description correctly states outputs. However, the missing region parameter in the schema undermines completeness. No caveats about tax law changes or rate variations are mentioned. Sufficient for a simple calculator but flawed.

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 lists 'region' as an input, but the actual schema does not include a region parameter; only 'amount' and 'relationship' are present. This is misleading and adds incorrect information. The schema coverage is 100%, but the description introduces a nonexistent parameter, reducing clarity.

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. It distinguishes itself from sibling calculators by specifying the domain (Belgian donation tax) and the regional variation (Bruxelles/Flandre/Wallonie).

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

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

The description gives a clear use case ('estate planning in Belgium') and mentions region specificity. It also references a related tool ('list_bundles') for further calculators, but does not explicitly state when not to use this tool or provide 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 full behavioral burden. It mentions using '2026 progressive brackets' and lists output fields, but lacks details on assumptions, limitations, or handling of edge cases (e.g., zero income). The output structure is disclosed, which is helpful.

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: purpose with method and output structure plus cross-reference. Every sentence is essential, no redundancy. Ideal 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?

For a simple one-parameter tool with full schema coverage and output structure mentioned, the description covers purpose, method, and related tools. It could mention residency or precision but is largely 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 a clear description for the single parameter (income). The description adds minimal extra meaning by mentioning '2026 progressive brackets', but does not clarify nuances like whether income is gross or net.

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 Belgian personal income tax for 2026, using specific terms like IPP/PB. It distinguishes from other tax calculators (e.g., Belgian salary, VAT) by focusing on personal income tax 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 specifies the context (Belgian personal income tax, 2026 brackets) and directs users to list_bundles for related tools. However, it does not explicitly state when not to use this tool, such as for corporate tax or other years.

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 correctly labels the tool as an 'estimate' and indicates it returns a monthly pension value. However, it does not disclose assumptions, limitations, or the non-destructive nature, leaving gaps in behavioral understanding.

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

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

The description is four sentences, front-loads purpose, and includes usage, inputs, output, and cross-reference. No wasted words, though structure could be improved by separating inputs/outputs more clearly.

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 tool (3 params, output schema exists), the description covers essential aspects: purpose, inputs, output, and related tools. It does not explain calculation methodology or assumptions, but for a straightforward calculator, this 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 coverage is 100%, giving baseline 3. However, description introduces 'status (employee/self-employed)' which does not match the actual schema parameter 'household_type' (enum: single/household). This mismatch reduces clarity and could mislead the agent. The description adds no value beyond schema for the other 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?

Description clearly states verb 'estimate' and specific resource 'Belgian retirement pension', distinguishing it from general pension calculators. It focuses on Belgian-specific retirement planning, which differentiates it from generic calculate_retirement_pension and other Belgian financial 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?

Explicitly says 'Use for retirement planning in Belgium' and cross-references list_bundles for related calculators, providing context. Does not explicitly state when not to use, but the scope 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?

Given no annotations, the description carries full burden. It states the calculation is an 'approximation' and lists key output fields including social contributions and taxes. This provides solid transparency about what the tool computes, though it could mention any limitations or assumptions.

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 with a clear list of return values and a helpful reference to list_bundles. Every element adds value, and the main purpose is front-loaded with no extraneous 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 tool with one input and outputs described, the description is complete. It explains the purpose, lists output fields, and points to related tools. Given the presence of an output schema (implied by the list), the description need not elaborate 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?

Schema coverage is 100% for the single parameter, which already describes 'Gross monthly salary in euros'. The description adds the word 'Belgian' to the context, but this is minor. Baseline 3 is appropriate since the schema does the heavy lifting.

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

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

The description clearly specifies the verb 'Convert' and the resource 'Belgian gross monthly salary to net salary (approximation)'. It distinguishes this tool from many calculate_ siblings by focusing on Belgian salary conversion and even references a related bundle for similar 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 implies usage context for converting Belgian gross salary, and it directs to list_bundles for related 'finance-belgique' calculators. However, it does not explicitly state when to use this tool versus others, nor does it provide prerequisites 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. The description does not disclose behavioral traits beyond the calculation nature. No mention of idempotency, side effects, authorization needs, or rate limits. For a pure calculation tool, this is minimal.

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 followed by a reference to list_bundles. It is concise and front-loaded, with no unnecessary words. Efficient communication.

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 (one parameter, output schema exists), the description is fairly complete. It explains purpose, return structure, and related tools. However, it lacks usage guidelines and behavioral transparency, leaving some gaps.

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?

Only one parameter (annual_income) with 100% schema coverage. The description adds no extra info beyond the schema's description, but the listing of return fields helps contextualize the parameter's effect. Baseline 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 Belgian self-employed social contributions (INASTI). It lists the return fields and references related calculators via list_bundles, distinguishing it from numerous 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?

No explicit guidance on when to use this tool vs alternatives. It only mentions 'See list_bundles for related calculators' but does not specify prerequisites, limitations, 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?

The description discloses the return structure ({amount_ht, amount_ttc, vat_amount, vat_rate}) but does not state other behavioral traits such as side effects or safety. With no annotations, the description carries the full burden, and this is insufficient for full 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 with no wasted words. Front-loaded with the core purpose, followed by output format and a related tools hint.

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

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

The description is adequate for a simple calculator but lacks details on edge cases, rate applicability, or any restrictions. The output schema is present but not shown; the description compensates partially by listing return fields. Still, completeness could be higher given the presence of many sibling calculators.

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 fully describes all parameters (100% coverage). The description adds no new semantic information beyond the schema, so baseline score of 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 the tool calculates Belgian VAT and converts between HT and TTC, with explicit return fields. The mention of 'Belgian' differentiates it from many country-specific VAT 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?

No guidance on when to use this tool versus alternatives like calculate_french_vat or calculate_vat_generic. The only hint is 'See list_bundles for related calculators,' which is minimal.

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 discloses the computation (cycle values, range -100 to +100, zone) and its pseudoscientific nature. It does not mention side effects or data handling, but for this simple calculator, the transparency is adequate.

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

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

The description is three sentences, compact and to the point. It includes necessary information but could be slightly more concise by omitting the subjective 'pseudoscience' label. Overall efficient for the tool's simplicity.

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 output schema exists (assumed to detail return values), the description covers the essence: inputs, outputs (3 cycle values, range, zone). It is complete for a trivial calculator with two date inputs. No missing critical details for correct usage.

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?

Both parameters (birth_date, target_date) have 100% schema coverage with format YYYY-MM-DD specified. The description merely restates 'Inputs: birth date, target date' without adding new meaning or constraints beyond the schema, resulting in no added semantic 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 it computes physical, emotional, and intellectual biorhythm cycles based on birth and target dates, with specific output values and range. It distinguishes itself from sibling calculators (e.g., financial, health) by labeling it a pseudoscience tool for self-tracking enthusiasts.

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 self-tracking enthusiasts and explicitly categorizes it as pseudoscience, providing context. It references list_bundles for similar 'fun' calculators but does not explicitly state when not to use or exclude 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 exist, so the description must carry full weight. It mentions the tool is an estimate and lists return fields, but lacks disclosure on assumptions, accuracy, or legal considerations. 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?

Two sentences, no unnecessary details. The first sentence states purpose and formula, the second lists return fields and a cross-reference. 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 existence of an output schema, the return format is covered. The tool has 4 required parameters all documented in the schema. However, the description could offer more context on when to use the estimate (e.g., educational vs. legal). Still, it is largely 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%, so the baseline is 3. The description adds no parameter-level details; it only describes the return format. The schema already documents parameters sufficiently.

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 blood alcohol content (BAC) using the Widmark formula, with specific return fields. It differentiates from siblings by referencing the famous formula and directing to 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?

The description does not explicitly state when to use this tool versus alternatives like calculate_alcohol_units or calculate_bac_points. Only a vague reference to bundles is provided, missing direct guidance on tool 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 provided; the description states the tool calculates and returns results, which implies no side effects. It does not explicitly confirm read-only behavior or mention any constraints, 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?

Two sentences, no filler. First sentence states core purpose, second provides cross-reference to 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 presence of an output schema (context indicates true) and the simple nature of the tool, the description covers key information: purpose and related tools. Missing input range validation detail, but schema handles that.

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 for both parameters, so the description adds no new meaning. The phrase 'weight category' is additional output context, but for parameters it adds nothing 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?

The description clearly states the tool calculates BMI and weight category, using specific verb 'Calculate' and resource. It distinguishes from siblings by mentioning 'list_bundles' for related calculators, making 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 hints at related tools via 'list_bundles' but provides no explicit when-to-use or when-not-to-use guidance. It does not differentiate from similar calculators like 'calculate_bmi_pet' or 'calculate_body_fat'.

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 reveals the algorithm used (Mifflin-St Jeor equation) and the return format ({bmr_kcal}), which are key behavioral traits. However, it does not mention any limitations, permissions, or side effects, though for a calculator these are minimal.

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 no fluff. The first sentence provides the core purpose, and the second sentence adds a useful pointer 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 that an output schema exists (as per context signals), the description is complete enough for a simple calculator. The reference to list_bundles covers discoverability of related tools. No additional information is 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?

The input schema has 100% coverage with each parameter described (e.g., 'weight_kg: Weight in kilograms'). The description adds no additional meaning beyond what the schema already provides, so a baseline score of 3 is appropriate.

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

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

The description clearly states it calculates Basal Metabolic Rate using the Mifflin-St Jeor equation. This verb+resource combination is specific and distinguishes it from the many other health calculators (e.g., calculate_bmi, calculate_body_fat) in the sibling list.

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

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

The description hints at related tools via 'See list_bundles for related 'sante' calculators,' but does not explicitly state when to use this tool versus alternatives like calculate_tdee or calculate_calories_burned. No exclusions or prerequisite conditions 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 are provided, so the description carries the burden. It only mentions the return format as '{body_fat_pct}', which is partially covered by the output schema. It does not disclose limitations (e.g., not for athletes), assumptions, or accuracy ranges of the Deurenberg equation.

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

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

The description is a single efficient sentence plus a referral to 'list_bundles'. Every word 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?

Despite its simplicity, the tool estimates a medical measure with known limitations (e.g., population specificity). The description omits important context like error margins, valid age ranges, or guidance on when the Deurenberg equation is appropriate. The output schema exists but does not compensate for these gaps.

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 for bmi, age, sex. The description adds only that they are used in the Deurenberg equation, providing no additional constraints or meaning beyond the schema. Baseline 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 'Estimate body fat percentage from BMI, age and sex using Deurenberg equation', specifying the verb 'estimate', the resource 'body fat percentage', and the inputs. It distinguishes from sibling tools 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 advises 'See list_bundles for related 'sante' calculators', but does not explicitly state when to use this tool versus alternatives like 'calculate_body_fat_navy'. It lacks clear conditions for use or 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?

With no annotations, the description bears full responsibility for behavioral disclosure. It only states the calculation method but does not mention any side effects, required permissions, rate limits, or whether the operation is read-only. The existence of an output schema is not referenced.

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 concise (one sentence plus a reference) and front-loaded with the key purpose. However, it is too sparse, omitting valuable context that could be included without redundancy. Every sentence earns its place, but more content is needed.

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 moderate complexity (6 parameters, 4 required, output schema) and no annotations, the description is incomplete. It does not explain the output format (e.g., body fat percentage, fat mass with weight input) or provide usage context beyond the method name.

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 parameter-specific information beyond what the schema already provides. It does not explain the significance of parameters like hip_cm (required for females) or default values.

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, specifying verb ('calculate'), resource ('body fat percentage'), and method ('US Navy circumference method'). This distinguishes it from sibling tools like calculate_body_fat and calculate_bmi.

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 such as calculate_body_fat (generic) or calculate_bmi. The reference to list_bundles for related calculators is vague and does not clarify specific use cases 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 cover behavioral traits. It only states the basic conversion without disclosing any limitations, precision, edge cases, or typical use scenarios. The transparency is low.

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, front-loaded with the core purpose, and ends with a useful cross-reference. Every word serves a purpose, and there is no redundancy.

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

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

Given the tool's simplicity (2 required parameters, enum for note values, presence of output schema), the description is adequate. It covers the essential purpose and a pointer to related tools. It does not need to elaborate on return values due to output schema existence.

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

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

The schema description coverage is 100% (2 parameters both described). The description adds no additional meaning beyond the schema; it simply reiterates the overall purpose. Baseline score of 3 is appropriate since the schema already documents 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 conversion from BPM to millisecond delay times for note values. It specifies the verb 'Convert', the resource 'BPM tempo', and the output 'millisecond delay times'. The reference to 'list_bundles' for related calculators provides some sibling differentiation, but the description could be more explicit about the audio context.

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 hint to see 'list_bundles' for related calculators, suggesting alternative tools. However, it does not explicitly state when to use this tool versus others, nor does it provide any exclusions or prerequisites. The guidance is minimal.

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

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

No annotations are present, so the description carries the full burden. It implies a safe, read-only calculation tool for education, with no side effects. However, it does not explicitly state that it is non-destructive or has no side effects.

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

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

The description is short (three sentences) and front-loaded with purpose and inputs. However, the inclusion of a non-existent 'reaction time' parameter wastes space and reduces clarity. The bundle reference is helpful but the erroneous detail detracts.

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 schema coverage is 100% and an output schema exists, the description adds value by specifying the educational use case and related bundle. However, it fails to explain how the road condition affects braking distance or clarify the missing reaction time parameter, leaving gaps for an AI agent.

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 'reaction time s' as an input, but the schema does not include a reaction time parameter, causing confusion. The schema already describes both parameters (speed_kmh and condition) with 100% coverage, but the description adds misleading information and does not clarify parameter 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 it computes reaction and braking distance based on road condition, with specific inputs (speed, reaction time, road type) and output (total stopping distance in meters). It distinguishes from sibling calculators by being specific to braking distance for driver safety education.

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 using it for driver safety education and points to a bundle for related calculators ('auto-transport'). It provides clear context but does not explicitly mention when not to use it or list 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 provided, so description carries full burden. It mentions inputs and outputs (ratio and meters per pedal turn) but does not disclose calculation details, edge cases (e.g., negative teeth), or any potential errors. Sufficient for a simple computation tool 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?

Two sentences, front-loaded with action. Every word earns its place. No wasteful phrasing.

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

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

Given the presence of an output schema (though not shown) and high schema parameter coverage, the description should clarify the return fields. It mentions ratio and meters per pedal turn but the wheel diameter discrepancy leaves a gap in 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?

Schema coverage is 100% with descriptions for chainring_teeth and cog_teeth. However, the description mentions 'wheel diameter mm' as an input, which is not in the schema. This inconsistency confuses the agent and reduces trust. The description adds context but is misleading.

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 'Compute cycling gear ratio (braquet) and development per pedal turn.' This is specific and distinguishes it from numerous sibling calculator tools. The domain is 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?

Provides context: 'Use for road cycling gear analysis.' and suggests related tools via 'See list_bundles for related 'sport' calculators.' However, it does not explicitly state when not to use this tool or list alternatives for non-road cycling.

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?

Since no annotations are provided, the description is the sole source. It conveys the calculation nature and output, but does not explicitly state that the tool is read-only or has no side effects. The description is straightforward and accurate, but minimal.

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. The first sentence delivers the core purpose and output. The second directs to related tools. Excellent structure for a simple tool.

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, the description covers the basic functionality and output. However, it omits parameter descriptions (0% schema coverage) and does not differentiate from sibling 'calculate_bra_size_convert'. It mentions related tools via 'list_bundles', but lacks full context for an AI agent to choose 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?

With 0% schema description coverage, the description should explain parameters. It mentions 'underbust and bust measurements (cm)' and system, but does not detail constraints like exclusiveMinimum or the enum values. The output schema is referenced, but input parameters lack explanation beyond their names.

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 bra size using underbust and bust measurements and system. It specifies the output fields. However, it does not explicitly differentiate from the sibling tool 'calculate_bra_size_convert', missing a chance to clarify tool boundaries.

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 guidance when to use this tool versus alternatives. The mention of 'list_bundles' is vague and does not help the agent decide. No when-to-use or when-not-to-use context 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 mentions the return format but lacks details on error handling, idempotency, or what happens with invalid inputs. The schema covers parameter constraints but the description adds minimal behavioral context beyond transformation.

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 redundancy. The first sentence conveys the core purpose, and the second provides a useful pointer 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?

For a simple conversion tool with three parameters and an output schema, the description is complete. It specifies the systems, return structure, and related tools. Nothing essential is missing.

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

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

Schema coverage is 100% with clear parameter descriptions. The description adds value by specifying the systems involved and the return format, which goes beyond the schema's individual parameter descriptions.

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

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

The description clearly states the verb 'Convert' and the resource 'bra size' with specific systems (FR, US, UK, EU). It distinguishes from similar conversion tools like convert_shoe_size by specifying the domain and referencing 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 says when to use: to convert bra size between the four systems. It also directs to list_bundles for related tools. However, it does not explicitly state when not to use or provide direct 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 clearly states that the tool performs a computation and returns results without side effects, which is appropriate for a calculator. It does not discuss error handling or limits, but the behavior is straightforward.

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 plus a link to related tools. It is highly concise and front-loaded with the key formula and usage, wasting no 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 calculator with good schema and output schema, the description covers the formula, inputs, and outputs completely. It also points to related tools, making it self-contained and informative.

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

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

Schema coverage is 100%, so the baseline is 3. The description mentions 'flour g, water g' which adds minimal extra meaning beyond the existing schema descriptions. No additional units or formats are contributed.

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 baker's hydration percentage with an explicit formula. It specifies inputs and outputs, but does not differentiate from the sibling 'calculate_hydration' which might have overlapping functionality.

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 provides context, but it does not explicitly state when not to use this tool or mention alternatives beyond a reference to list_bundles for related calculators.

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 inputs and outputs ('Returns break-even units and revenue'), but does not elaborate on behavioral traits like idempotency or side effects. Given it's a calculator, the description is adequate but not rich.

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: first covering purpose and outputs, second listing inputs and referring to related tools. No extraneous words, front-loaded, and 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 tool has 3 parameters, no annotations, and an output schema (present). The description covers purpose, usage context, inputs, outputs, and points to related tools, making it sufficiently complete for an agent to invoke correctly.

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

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

Schema coverage is 100%, so baseline is 3. The description lists the three inputs in a sentence ('fixed costs, price/unit, variable cost/unit'), adding grouping context but no additional semantics beyond the schema's property descriptions.

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

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

The description clearly states 'Compute break-even point in units and revenue.' with a specific verb and resource. It distinguishes from sibling tools by referencing related 'finance-universal' calculators via list_bundles. This makes 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 explicitly says 'Use for business plans and pricing decisions,' providing clear context. It also directs to list_bundles for related tools, aiding in tool selection. However, it does not specify when not to use this tool or provide explicit 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 burden. It describes the computation and return values ('Returns due date and gestation milestones') but does not disclose any permissions, rate limits, or side effects. For a calculation tool, 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 with two sentences. The first sentence states the purpose, and the second lists inputs and output. It is front-loaded and efficient, though could be more structured with bullet points.

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

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

With many sibling calculators, the description references list_bundles for related tools. It mentions output (due date, gestation milestones) but lacks specifics on gestation periods, assumptions, or error handling. The description is incomplete due to the species mismatch and lack of 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 description coverage is 0%, so the description must explain parameters. It lists species and mating date, but lists 'horse' and 'cow' which are not in the schema enum, and omits 'hamster' from the description. This mismatch could mislead an agent. It adds some meaning but introduces inaccuracies.

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 due date for animal breeding given mating date and species gestation period. It lists supported species and output, though there is a mismatch between description (horse, cow) and schema enum (hamster missing, horse/cow not present). It distinguishes from many sibling calculators by referencing 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 says 'Use for breeders' but does not explicitly state when not to use or provide alternatives. A reference to list_bundles suggests related calculators but no direct exclusions or when to choose this over other animal pregnancy calculators.

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 bears full burden. It mentions inputs and returns but does not disclose any behavioral traits such as whether it modifies data, requires permissions, or has side effects. Since it's a pure calculation, destructive behavior is unlikely, but transparency remains low.

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 brief, front-loaded with purpose and usage guidelines. Three sentences cover the essential information without superfluous 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 parameters and no annotations, the description adequately states inputs and outputs. It references the output schema indirectly ('Returns total points and mention'). While it lacks details on calculation formula or mention types, the existence of an output schema likely covers return specifics.

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 and bounds. The description adds no additional meaning beyond what the schema already provides. 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?

Description clearly states the tool estimates French Brevet (DNB) score from grades and continuous-control marks. It specifies the verb 'Estimate' and resource 'French Brevet score', and distinguishes from siblings by noting it's for collège students 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?

Provides explicit usage context: 'Use for collège students forecasting their result.' Also references list_bundles for related 'education' calculators, guiding users to alternatives. While it doesn't state when not to use, the scope is narrow enough that this 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, so the description must fully disclose behavioral traits. It mentions computation and returns, but does not state if the tool is read-only, idempotent, or has side effects. While a calculator is likely safe, the description should have explicitly stated it is a read-only query.

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: the first states purpose and key feature, the second lists inputs/outputs and points to related tools. Every sentence earns its place with 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 there is an output schema (not shown), the description need not detail return values, but it does mention 'brick count and pallets'. It lacks clarification on units (implied meters from schema) and the missing waste % parameter reduces completeness. It points to list_bundles for related calculators, which is helpful.

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 descriptions, so baseline is 3. However, the description mentions 'brick size' and 'waste %' as inputs, but the schema has only type, height_m, length_m, and no waste % parameter. This mismatch misleads the user and adds confusion rather than clarity.

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 bricks or blocks for a wall with waste margin, using the verb 'compute' and specifying 'masonry projects'. It is specific to masonry, but does not explicitly differentiate from other construction calculators like calculate_tile_quantity, so it loses a point for sibling distinction.

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 masonry projects' and suggests seeing list_bundles for related tools, which implies a general context but lacks explicit when-not-to-use or alternative tools. Prerequisites like units are in the schema but not restated in the description.

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

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

With no annotations provided, the description carries the full burden. It clearly states that the tool returns 'buoyant force and float/sink verdict,' which is sufficient behavioral disclosure for a calculation tool with no destructive side effects.

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

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

The description is concise at four sentences, front-loading the purpose and key inputs/outputs. However, the mention of 'See list_bundles' adds a tangential instruction that slightly dilutes focus.

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 physics calculator, the description provides essential information: purpose, inputs, outputs, and usage context. The existence of an output schema compensates for lack of detail on return values. It does not cover edge cases or assumptions, but that is acceptable for this 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%, and the description reiterates the input parameters (mass, volume, fluid density) without adding new constraints, relationships, or format details beyond what the schema provides. Baseline 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 computes buoyancy force and floating analysis using Archimedes' principle, specifying the resource and actions. However, it does not directly differentiate this tool from siblings like calculate_density or calculate_force, which could also relate to physics or shipping.

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' and mentions inputs (mass, volume, fluid density). It does not explicitly state when not to use it or compare to alternative tools, only a vague reference to list_bundles for related calculators.

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 inputs and outputs (burn, runway, profitability date) and implies read-only calculation. For a calculator, this is sufficient, though no explicit statement of safety or permissions.

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: action, usage context, inputs/outputs, and reference to related tools. No wasted words, front-loaded with 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 calculator nature, full schema coverage, and output schema existence, the description covers purpose, usage, inputs, and outputs adequately. Missing potential warnings or edge cases but acceptable for this type of 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 descriptions. The description adds value by summarizing inputs and explaining output components, enhancing 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 it computes startup monthly burn rate and runway, with specific verb 'Compute' and resource 'burn rate and runway'. It references related calculators for differentiation, making the purpose distinct.

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 when to use (fundraising, expense control) but lacks explicit guidance on when not to use or how it compares to siblings like calculate_emergency_fund or calculate_break_even. Only mentions list_bundles for alternatives, which is weak.

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 traits. It only states 'Returns required section' without detailing error handling, assumptions (e.g., conductor material), or limits. This is minimal 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 three sentences long, front-loads the purpose, and is efficient. Minor waste: 'See list_bundles for related...' could be trimmed but is acceptable.

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 4 parameters, 2 required, and an output schema, the description provides basic context (standard, residential use) but lacks details on valid ranges, edge cases, or how to handle errors. It is moderately 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 the description should add value. However, it states 'power kW' while the schema property is 'power_w' (watts), creating a unit contradiction. This misleads the agent and adds no useful semantic 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 clearly states the tool computes cable cross-section per NF C 15-100 for residential wiring, which is a specific verb and resource. It does not explicitly differentiate from the sibling 'calculate_cable_section_electrical', but the mention of the French standard provides some distinction.

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 residential wiring' and directs to 'list_bundles' for related calculators, offering some context. However, it does not specify when not to use this tool or compare with alternatives like 'calculate_cable_section_electrical'.

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 states that the tool calculates and returns specific values, but does not disclose any behavioral traits like assumptions, formula details, or potential side effects. The disclosure is minimal but not misleading.

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

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

The description is concise with two sentences. The first sentence states purpose, the second lists return values and a pointer. It is front-loaded and efficient, though the pointer to 'list_bundles' could be more targeted.

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 (4 parameters, no nested objects), the description covers the core inputs and outputs. The return fields are explicitly listed, which substitutes for an output schema. However, it lacks details on formulas or assumptions, which would be useful for advanced users.

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 lists the parameters but adds no additional meaning beyond the schema's own descriptions. It does not explain units or default values, so it adds minimal 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 verb 'Calculate' and the resource 'cable section', and lists the key inputs (power, voltage, distance, max voltage drop). However, it does not explicitly differentiate from the sibling 'calculate_cable_section', which may be similar.

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 guidance on when to use this tool versus alternatives, such as the sibling 'calculate_cable_section'. The mention of 'list_bundles' for related calculators is vague and does not provide specific exclusions or 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. It mentions it returns ratio and health verdict, but does not disclose potential edge cases (e.g., zero inputs) or side effects. More detail on return format or error handling would be beneficial.

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 sentences, each serving a clear purpose: state purpose, provide usage context and target, list inputs/outputs and point to related tools. 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 output schema exists, the description sufficiently covers key aspects: purpose, inputs, outputs, and usage context. It lacks mention of error conditions but is complete for a simple calculator.

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 descriptions. The description just restates inputs as 'total CAC, LTV' without adding new semantics 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 it computes CAC/LTV ratio for SaaS unit economics. It specifies the resource (ratio) and provides a target (≥3.0). While it doesn't explicitly differentiate from all sibling calculators, the SaaS context helps distinguish 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?

It says 'Use for SaaS unit economics analysis' and gives a target ratio, providing clear usage context. However, it does not explicitly state when not to use this tool or directly name alternatives, only referencing list_bundles for related calculators.

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 the key behavioral assumption of a 5-hour half-life and mentions the output includes a clearance forecast. However, it does not detail limitations like single-dose assumption or accuracy, leaving some behavioral gaps. Since no annotations are provided, the description carries the full burden.

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 efficient sentences, front-loaded with purpose, use case, and input/output summary. 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?

With an output schema present, the tool is adequately complete for a simple calculator. It states outputs and directs to related tools. However, it assumes a single-dose model without mentioning multi-dose scenarios.

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, so baseline is 3. The description reiterates inputs (mg, hours) but adds no new semantic meaning beyond the schema. The 'sleep planning' context adds minor value for understanding the hours parameter.

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

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

The description clearly states the tool computes remaining caffeine using a 5-hour half-life, specifying the action and resource. It distinguishes itself from sibling tools like calculate_caffeine_half_life and calculate_caffeine_intake by focusing on clearance 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 directs to list_bundles for related calculators, but does not explicitly mention when not to use or contrast with other caffeine 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?

With no annotations provided, the description bears full responsibility for behavioral disclosure. It mentions the output format and that it calculates remaining caffeine, but it does not disclose whether the tool is read-only, what the underlying model assumptions are (e.g., half-life of 5-6 hours?), or any side effects. The description lacks depth for a mutation-like calculation tool.

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

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

The description is concise with two sentences, front-loading the core purpose. It could be slightly improved by separating the output info into a bullet or separate line, but it is effective and not verbose. 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?

The description covers the basic purpose and output fields, which is adequate for a simple calculation tool. However, it lacks usage guidelines and behavioral transparency, making it incomplete for an agent to use confidently. The absence of an explicit output schema (though described inline) slightly reduces 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% coverage with descriptions for both parameters (mg_consumed and hours_since). The tool description does not add additional meaning beyond what the schema provides. Baseline score of 3 is appropriate since the schema already documents the parameters adequately.

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 specific resource 'remaining caffeine in body after time elapsed'. It also mentions the output fields (hours_to_below_25mg, safe_to_sleep), which helps distinguish it from sibling tools like calculate_caffeine_clearance. However, it does not explicitly differentiate from all related caffeine calculators, so it's not a perfect 5.

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 vs alternatives. It only mentions to 'See list_bundles for related "sante" calculators', but does not offer criteria for choosing this one over similar tools like calculate_caffeine_clearance or calculate_caffeine_intake. No when-not-to-use or prerequisite information is given.

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

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

No annotations are provided, so the description carries the full burden. It discloses the return values (total mg, % of limit, time-of-day distribution) and implies it is a read-only calculation. It does not mention any side effects or destructive behavior, which is appropriate for this 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 three sentences, each adding value: purpose, usage scenario, and a reference to related tools. It is front-loaded with the key information and contains no waste.

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 does not need to fully detail return values, but it does anyway. It covers purpose, input format, output summary, and a sibling reference, making it complete for an AI agent to understand and invoke the tool correctly.

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