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

No annotations are provided, so the description carries the full burden of behavioral disclosure. However, it fails to describe any behavioral traits—such as whether this tool creates, modifies, or outputs data; what permissions or inputs are needed; or any side effects like file generation. The description is too minimal to inform the agent about how the tool behaves, making it opaque and risky to invoke.

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, concise phrase in Korean, which is appropriately sized for a simple tool. It is front-loaded with the core idea but lacks detail that could earn a higher score. While efficient, it under-specifies the tool's purpose, slightly reducing its effectiveness despite the brevity.

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 (2 parameters, nested objects, no output schema) and lack of annotations, the description is incomplete. It does not explain what the tool outputs (e.g., a formatted report, code, or text), how results are structured, or any behavioral context. For a tool that likely generates statistical reports, this leaves critical gaps, making it inadequate for the agent to use confidently.

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

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

The input schema has 100% description coverage, with parameters 'test_type' and 'results' documented in the schema itself. The description adds no additional meaning about these parameters—it does not explain what 'test_type' values are expected or how 'results' should be structured. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, but the description misses an opportunity to clarify usage (e.g., example test types).

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 'APA 스타일 통계 보고 템플릿' (APA style statistical reporting template) is vague and tautological—it essentially restates the tool name 'apa_reporting' in Korean with minimal added context. While it hints at generating APA-style reports, it lacks a specific verb (e.g., 'generate' or 'create') and does not clearly distinguish this tool from siblings like 'write_results_section' or 'code_template', which might also produce formatted outputs. This leaves the agent uncertain about the exact action.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, context (e.g., after statistical tests), or exclusions, nor does it reference sibling tools like 'write_results_section' for comparison. Without this, the agent must guess based on the tool name alone, which is insufficient for reliable selection.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. However, the description only lists parameter names ('사전분포, 수렴진단, 해석') without explaining what the tool does behaviorally—e.g., whether it generates code, provides explanations, runs analyses, or requires specific data inputs. This leaves the agent with no understanding of the tool's actions or traits.

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

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

The description is a single, efficient phrase that lists key aspects without unnecessary words. It's appropriately sized for a tool with 3 parameters and no output schema, though it could be more front-loaded with purpose rather than parameter names. There's minimal waste, but it lacks structural clarity in conveying intent.

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 Bayesian analysis and the lack of annotations or output schema, the description is incomplete. It fails to explain what the tool produces (e.g., a guide document, code snippets, diagnostic plots) or how it integrates with other tools. For a statistical guidance tool with no behavioral context, this leaves significant gaps for an agent to understand its role and outputs.

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

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

Schema description coverage is 100%, so the schema already documents all parameters with descriptions. The description lists parameter names ('사전분포, 수렴진단, 해석') but adds no meaningful semantics beyond what's in the schema—it doesn't clarify usage, constraints, or interactions. With high schema coverage, the baseline score of 3 is appropriate as the description doesn't compensate but also doesn't detract.

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 '베이지안 분석 가이드 (사전분포, 수렴진단, 해석)' translates to 'Bayesian analysis guide (prior distribution, convergence diagnosis, interpretation)', which is a tautology that restates the tool name 'bayesian_guide' and lists input parameters rather than specifying what the tool actually does. It doesn't distinguish this Bayesian guide from sibling tools like 'ml_for_causal' or 'sem_guide' that might also involve statistical guidance.

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. It doesn't mention any context, prerequisites, or exclusions, and with many sibling tools available (e.g., 'get_method_guide', 'suggest_method'), there's no indication of how this Bayesian-specific guide fits into broader workflows or when it's preferred over other methods.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions '계산 및 해석' (calculation and interpretation), implying it performs computations and provides insights, but fails to describe critical behaviors like input validation, error handling, output format, or computational limits. For a tool with no annotations, this is a significant gap in transparency.

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

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

The description is extremely concise—a single phrase listing the tool's function and examples. It is front-loaded with the core purpose and wastes no words, making it efficient for quick understanding without unnecessary elaboration.

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

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

Given no annotations, no output schema, and a nested 'values' parameter, the description is incomplete. It does not explain how to structure the 'values' object, what the tool returns, or any behavioral aspects like error cases. For a computational tool with complex inputs, this leaves too many gaps for effective 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%, so the schema already documents the two parameters ('type' with enum and 'values' as an object). The description lists effect size types (e.g., Cohen's d, η²) which align with the 'type' enum, adding some context, but does not explain the structure or content of the 'values' object. Baseline 3 is appropriate as 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 states the tool's purpose: '효과크기 계산 및 해석' (effect size calculation and interpretation) with specific examples (Cohen's d, η², f², OR, RR). It uses a specific verb ('계산 및 해석') and resource ('효과크기'), but does not explicitly distinguish it from sibling tools like 'meta_effect_size' or 'interpret_coefficient', which might have overlapping functions.

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. It lists effect size types but does not specify contexts, prerequisites, or compare to sibling tools such as 'meta_effect_size' for meta-analysis or 'interpret_coefficient' for interpretation. This lack of usage context leaves the agent without clear direction.

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 for behavioral disclosure. The description only states what the tool does (calculates power) without mentioning any behavioral traits - no information about what statistical methods are used, what assumptions are made, whether it's a read-only calculation, what format the output takes, or any limitations. This is inadequate for a statistical calculation tool with no annotation coverage.

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 - a single Korean sentence that directly states the tool's purpose. There's no wasted language or unnecessary elaboration. However, the extreme brevity comes at the cost of completeness, which affects other dimensions.

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 statistical calculation tool with 4 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what statistical methods are used, what assumptions underlie the calculation, what format the result takes, or how it differs from related sibling tools. The description leaves too many contextual questions unanswered for effective tool selection and 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%, so the schema already documents all four parameters (test_type, n, effect_size, alpha) with descriptions. The tool description adds no additional parameter information beyond what's in the schema. This meets the baseline of 3 when schema coverage is high, but doesn't provide 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?

The description clearly states the tool's purpose as 'calculating statistical power given sample size' (주어진 표본크기에서 검정력 계산), which is a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'calc_sample_size' or 'power_curve' that likely handle related power analysis functions, so it doesn't reach the highest clarity level.

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. With multiple sibling tools related to statistical calculations (calc_effect_size, calc_sample_size, power_curve, mde_calculator), there's no indication of when this specific power calculation tool is appropriate versus other options.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. While it indicates this is a calculation tool (implied read-only), it doesn't specify whether this is a statistical simulation, formula-based calculation, or what format the output takes. There's no mention of computational requirements, accuracy limitations, or what happens with invalid parameter combinations. For a statistical calculation tool with zero annotation coverage, this represents significant behavioral transparency gaps.

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

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

The description is extremely concise - a single phrase listing the tool's purpose and supported test types. While efficient, it might be too brief given the tool's complexity (6 parameters, statistical calculations). However, every word earns its place by communicating essential information 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 statistical calculation tool with 6 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what the tool returns (sample size number? confidence intervals? formula details?), doesn't provide usage examples or context, and doesn't address common statistical assumptions or limitations. Given the complexity and lack of structured documentation elsewhere, the description should provide more contextual information.

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

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

With 100% schema description coverage, the schema already documents all 6 parameters thoroughly. The description adds no parameter-specific information beyond what's in the schema - it doesn't explain parameter relationships, provide examples of effect size values for different test types, or clarify how parameters interact. The baseline score of 3 reflects adequate parameter documentation through the schema alone.

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 as '필요 표본크기 계산' (calculate required sample size) and lists specific statistical tests it supports (t-test, ANOVA, regression, proportion). This provides a specific verb+resource combination, though it doesn't explicitly differentiate from sibling tools like 'calc_power' or 'mde_calculator' which might have related statistical calculation purposes.

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. With multiple sibling tools for statistical calculations (calc_power, calc_effect_size, mde_calculator, etc.), there's no indication of when this sample size calculator is appropriate versus other statistical tools. The description simply lists what it does without contextual usage information.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only lists design types and aspects without explaining what the tool does behaviorally—e.g., whether it generates text, provides summaries, or returns structured data. There's no mention of output format, potential errors, or any operational traits, leaving significant gaps in understanding how the tool functions.

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, consisting of a single phrase that lists key terms. It's front-loaded with the main topic but lacks structure or elaboration. While efficient, it may be overly terse for a tool with multiple parameters and no output schema, potentially under-specifying its purpose. However, it avoids redundancy and 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 the complexity of causal inference methods and the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns, how to interpret results, or any behavioral context. With sibling tools covering similar topics, more detail is needed to distinguish this tool's role and ensure users can apply it correctly without confusion.

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%, with clear enum values for 'design' and 'aspect' parameters documented in the schema. The description adds no additional semantic meaning beyond what's in the schema, such as explaining the relationships between designs and aspects or providing usage examples. Since the schema is comprehensive, a baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract.

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 '인과추론 설계 가이드 (DID, RDD, IV, PSM, Synth)' states it provides guidance for causal inference designs, listing specific methods. However, it's vague about what the guidance entails (e.g., explanations, examples, or templates) and doesn't clearly distinguish it from sibling tools like 'get_method_guide' or 'suggest_method', which might overlap in purpose. The description is in Korean, which adds specificity but doesn't fully clarify the tool's function beyond a general topic.

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. It doesn't mention any prerequisites, context for selection among the listed designs, or comparisons to sibling tools such as 'event_study_guide' or 'psm_guide', which might cover similar ground. Without explicit usage instructions, users must infer based on the parameter names alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states it's a 'guide' for checking assumptions, which suggests it might provide explanations or recommendations rather than perform computations, but it does not clarify output format, whether it requires data input, or any operational constraints (e.g., rate limits, permissions). This lack of detail is a significant gap for a tool with no structured behavioral hints.

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 phrase in Korean that conveys the core purpose without unnecessary words. It is front-loaded with the main idea, though it could be slightly more structured (e.g., by specifying the tool's output). There is no wasted text, making it concise and easy to parse.

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

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

Given the complexity implied by statistical assumption checking, lack of annotations, and no output schema, the description is incomplete. It does not explain what the tool returns (e.g., a guide text, code, or diagnostic results), how to interpret outputs, or any behavioral nuances. This leaves the agent with insufficient context to use the tool effectively beyond basic parameter input.

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

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

Schema description coverage is 100%, with parameters 'method' (analysis method) and 'data_description' (data description) documented in the schema. The description does not add any meaning beyond this, such as examples or constraints for the parameters. With high schema coverage, the baseline score of 3 is appropriate, as the description doesn't compensate but doesn't need to given the schema's completeness.

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 '통계 가정 점검 가이드 (정규성, 등분산, 독립성 등)' translates to 'Statistical assumption checking guide (normality, homoscedasticity, independence, etc.)', which provides a general purpose (guide for checking statistical assumptions) but is vague about the specific action (e.g., whether it generates code, explains methods, or performs tests). It distinguishes from siblings by focusing on assumption checking rather than other statistical tasks, but lacks a clear verb+resource combination.

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 offers no explicit guidance on when to use this tool versus alternatives. While it implies usage in statistical analysis contexts, it does not specify scenarios, prerequisites, or comparisons to sibling tools like 'diagnose_regression' or 'interpret_diagnostics', which might overlap. This leaves the agent without clear direction for 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 are provided, so the description carries the full burden of behavioral disclosure. However, it offers no information about the tool's behavior—such as whether it generates, modifies, or retrieves code templates, what permissions might be needed, or what the output looks like. This leaves critical behavioral traits completely undocumented.

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, vague phrase that is under-specified rather than concise. It fails to front-load key information or structure content effectively, leaving the agent with insufficient detail to understand the tool's function. While brief, it lacks the clarity needed for efficient comprehension.

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

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

Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., code snippets, file paths, or structured data) or provide any behavioral context. For a tool with two required parameters and no structured output documentation, this minimal description is inadequate to guide proper 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?

The schema description coverage is 100%, with both parameters ('workflow' and 'language') fully described in the schema via enums and descriptions. The description adds no additional meaning or context beyond what the schema already provides, so it meets the baseline score of 3 for high schema coverage without compensating 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 '분석 전체 워크플로우 코드 템플릿' (analysis entire workflow code template) is vague and tautological—it essentially restates the tool name 'code_template' with minimal added specificity. It mentions 'workflow' and 'code template' but doesn't clarify what the tool actually does (e.g., generates, retrieves, or applies templates). Compared to siblings like 'generate_python_code' or 'write_analysis_file', it lacks a clear verb and distinct 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 no guidance on when to use this tool versus alternatives. It doesn't mention any context, prerequisites, or exclusions, and fails to differentiate it from sibling tools such as 'generate_python_code', 'generate_r_code', or 'meta_code'. Without any usage instructions, the agent is left guessing about its appropriate application.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. While it mentions the tool compares methods' 'advantages/disadvantages' and 'application conditions', it doesn't describe what the comparison output looks like, whether it's a summary table or detailed analysis, if there are limitations to the comparison, or what format the results take. For a tool with no annotations and no output schema, this leaves significant behavioral questions unanswered.

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 - a single phrase that efficiently communicates the core functionality. Every word earns its place: '여러 통계 방법 비교' establishes the action and target, while '(장단점, 적용조건)' adds valuable context about what aspects are compared. There's no wasted language or unnecessary elaboration.

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 there are no annotations and no output schema, the description is insufficiently complete. While concise, it doesn't explain what the comparison output looks like, how results are structured, or what limitations might exist. For a tool that presumably generates comparative analysis of statistical methods, users need more context about the nature and format of the comparison results.

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

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

Schema description coverage is 100%, with both parameters ('methods' and 'criteria') having descriptions in the schema. The tool description doesn't add any parameter-specific information beyond what's already in the schema. It mentions 'advantages/disadvantages, application conditions' which somewhat relates to the 'criteria' parameter, but doesn't provide additional semantic context about parameter usage or constraints.

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

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

The description clearly states the tool's purpose: '여러 통계 방법 비교 (장단점, 적용조건)' translates to 'Compare multiple statistical methods (advantages/disadvantages, application conditions)'. This specifies the verb (compare) and resource (statistical methods) with additional context about what aspects are compared. However, it doesn't explicitly differentiate from sibling tools like 'suggest_method' or 'get_method_guide' 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 provides no guidance on when to use this tool versus alternatives. With many sibling tools related to statistical methods (suggest_method, get_method_guide, test_selection, etc.), there's no indication of when this comparison tool is appropriate versus those other options. The description only states what the tool does, not when to use it.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. '생성' implies a write operation, but the description doesn't specify whether this creates physical folders, requires specific permissions, has side effects, or what happens on failure. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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

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

The description is a single, efficient phrase in Korean that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, with every element earning its place.

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

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

Given the tool's complexity (a mutation operation creating folder structures), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns, error conditions, or behavioral details, making it inadequate for safe and effective use by 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?

Schema description coverage is 100%, so the schema already documents all three parameters (project_name, base_path, template with enum values). The description adds no additional meaning about parameters beyond what's in the schema, such as format examples or constraints, resulting in the baseline score of 3.

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

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

The description clearly states the action ('생성' meaning 'create') and resource ('연구 프로젝트 폴더 구조' meaning 'research project folder structure'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'code_template', 'prereg_template', or 'replication_package' that might also involve project structure creation, which prevents a perfect score.

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. There's no mention of prerequisites, context, or comparison with sibling tools like 'code_template' or 'replication_package', leaving the agent to guess based on the tool name alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states it provides 'help' without explaining what the tool actually does (e.g., analyzes code, suggests fixes, returns explanations), its limitations, or any behavioral traits like error handling or output format.

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

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

The description is overly concise to the point of under-specification—a single phrase in Korean that lacks structure or front-loading of key information. It fails to earn its place by not providing actionable details, making it inefficient rather than succinct.

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 (3 parameters, no annotations, no output schema) and rich sibling context, the description is severely incomplete. It does not explain what the tool returns, how it behaves, or its scope, leaving critical gaps for an agent to understand and use it effectively.

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

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

Schema description coverage is 100%, so the schema fully documents the three parameters (code, error_message, language). The description adds no meaning beyond this, such as examples or constraints, but the high coverage justifies a baseline score of 3 as adequate.

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 '통계 코드 디버깅 도움' (statistical code debugging help) restates the tool name 'debug_code' in Korean with minimal elaboration, making it tautological. It specifies the domain (statistical code) but lacks a clear verb or distinct differentiation from sibling tools like 'optimize_code' or 'diagnose_regression', leaving the exact action vague.

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 is provided on when to use this tool versus alternatives. With many sibling tools for code-related tasks (e.g., 'optimize_code', 'generate_python_code'), the description offers no context, exclusions, or prerequisites, failing to help an agent choose appropriately.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool is a 'diagnosis guide' but doesn't clarify behavioral traits like whether it performs computations, provides textual guidance, requires specific inputs beyond parameters, or has any side effects. This leaves significant gaps in understanding how the tool operates beyond its basic purpose.

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 phrase in Korean that conveys the core purpose without unnecessary elaboration. It's front-loaded with key terms but could be slightly more structured for clarity. Overall, it's concise and to the point, 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 regression diagnostics, no annotations, and no output schema, the description is insufficient. It doesn't explain what the tool returns (e.g., diagnostic reports, recommendations, or test results), behavioral details, or how to interpret outputs. This leaves the agent with incomplete information for effective use in a statistical context.

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

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

Schema description coverage is 100%, with parameters 'issues' and 'model_type' well-documented in the schema. The description adds minimal value by listing examples (multicollinearity, heteroscedasticity, autocorrelation) that align with the schema's description for 'issues', but it doesn't provide additional context like parameter interactions or usage tips. Baseline 3 is appropriate as the schema handles most documentation.

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 '회귀분석 진단 가이드 (다중공선성, 이분산, 자기상관 등)' translates to 'Regression analysis diagnosis guide (multicollinearity, heteroscedasticity, autocorrelation, etc.)', which indicates the tool provides diagnostic guidance for regression analysis. However, it's vague about the exact action (e.g., whether it generates reports, runs tests, or offers advice) and doesn't clearly distinguish from sibling tools like 'check_assumptions' or 'interpret_diagnostics', which might overlap in 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 lacks explicit guidance on when to use this tool versus alternatives. It mentions diagnostic aspects but doesn't specify contexts, prerequisites, or exclusions, such as when to choose it over 'check_assumptions' or 'interpret_diagnostics'. No usage scenarios or comparisons are provided, leaving the agent with minimal direction.

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 doesn't disclose any behavioral traits such as whether it generates code, provides explanations, requires specific inputs beyond parameters, or has side effects. The term '가이드' (guide) implies informational output, but this is not explicitly stated, leaving the tool's behavior unclear.

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, concise phrase that is front-loaded with the key term '사건연구(Event Study)'. There is no wasted text, but it may be overly terse given the lack of detail. It efficiently conveys the topic 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?

Given no annotations, no output schema, and a vague description, the tool definition is incomplete. The description doesn't clarify what the tool produces (e.g., a report, code, or instructions), leaving significant gaps in understanding its function and output. For a tool with 3 parameters and complex context (event study design), this is inadequate.

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

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

Schema description coverage is 100%, so the schema already documents all parameters (event_type, staggered, estimator) with descriptions and an enum for estimator. The description adds no additional meaning beyond what the schema provides, such as explaining relationships between parameters or usage examples. With high schema coverage, the baseline score of 3 is appropriate.

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

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

The description '사건연구(Event Study) 설계 가이드' (Event Study Design Guide) states the general purpose but is vague about what the tool actually does. It mentions '설계 가이드' (design guide) which suggests guidance or assistance, but doesn't specify a clear action verb like 'generate', 'create', or 'analyze'. It distinguishes from siblings by focusing on event studies, but lacks specificity about the output or function.

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. It doesn't mention prerequisites, context, or compare to sibling tools like 'causal_design_guide' or 'timeseries_guide'. Users must infer usage from the title alone, which is insufficient for effective 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 are provided, so the description carries the full burden. It mentions generating code but doesn't disclose behavioral traits such as whether it creates files, outputs strings, requires authentication, has rate limits, or handles errors. This leaves significant gaps in understanding how the tool behaves.

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 a single phrase, making it efficient and front-loaded. However, it could be more structured by including key details, but it avoids unnecessary verbosity.

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

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

Given the tool's complexity (3 parameters, no output schema, no annotations), the description is incomplete. It lacks details on what the generated code does, output format, error handling, or how it integrates with siblings, making it inadequate for effective 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%, so the schema documents parameters well. The description adds minimal value by implying the code generation relates to statsmodels and sklearn, which loosely maps to the 'library' parameter, but doesn't elaborate on parameter meanings or usage beyond what the schema provides.

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

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

The description states the tool generates Python code for statsmodels and sklearn, which clarifies the verb (generate) and resource (Python code). However, it doesn't distinguish from sibling tools like generate_r_code or generate_stata_code beyond mentioning specific libraries, and the purpose remains somewhat vague regarding what kind of code is generated.

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 is provided. The description mentions libraries but doesn't specify contexts, prerequisites, or exclusions compared to siblings like code_template or write_analysis_file, leaving usage unclear.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool generates R code but doesn't describe how it behaves—e.g., whether it creates files, returns code snippets, requires specific inputs, or has any side effects like saving outputs. This leaves significant gaps in understanding the tool's operation.

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—a single phrase in Korean—and front-loaded with the core purpose. However, it could be more structured by elaborating slightly to improve clarity without losing efficiency, as it currently feels under-specified rather than optimally concise.

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

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

Given the tool has 3 parameters, no annotations, no output schema, and involves code generation (a potentially complex operation), the description is incomplete. It doesn't explain what the tool returns, how to use the parameters effectively, or any behavioral traits, making it inadequate for full contextual understanding despite the schema covering parameters.

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

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

Schema description coverage is 100%, so the schema already documents the three parameters (analysis_type, variables, options) with basic descriptions. The description adds no additional meaning beyond implying these are used for analysis, diagnosis, and visualization, which aligns with but doesn't enrich the schema details. Baseline 3 is appropriate as the schema handles parameter documentation 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 'R 코드 생성 (분석, 진단, 시각화)' translates to 'R code generation (analysis, diagnosis, visualization)', which provides a general purpose but lacks specificity about what resources or data it operates on. It distinguishes from some siblings like generate_python_code by specifying R, but remains vague about the exact scope compared to other code-related tools like visualization_code or table_code.

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 is provided. The description implies it's for generating R code, but it doesn't specify contexts, prerequisites, or exclusions, such as when to choose this over generate_python_code or other code-generation siblings like code_template or meta_code.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool generates code but doesn't specify if it's read-only, requires authentication, has rate limits, or what the output format is. For a code generation tool with zero annotation coverage, this is a significant gap in transparency about its behavior and 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?

The description is very concise with a single phrase 'Stata 코드 생성 (분석, 진단, 시각화)', which is efficient and front-loaded. However, it might be overly brief, potentially under-specifying the tool's purpose. Every word earns its place, but it could benefit from slightly more detail without becoming verbose.

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

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

Given the complexity of a code generation tool with 3 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns, any behavioral traits, or usage context. For a tool that likely produces structured output, the lack of output schema and minimal description leaves significant gaps in understanding how to use it effectively.

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

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

The schema description coverage is 100%, with parameters 'analysis_type', 'variables', and 'options' all having descriptions in the schema. The description doesn't add any meaning beyond what the schema provides, such as examples or clarifications. Given the high schema coverage, a baseline score of 3 is appropriate as the schema handles the parameter documentation 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 'Stata 코드 생성 (분석, 진단, 시각화)' states the tool generates Stata code for analysis, diagnosis, and visualization, which is a clear purpose. However, it's somewhat vague about the specific scope and doesn't differentiate from sibling tools like 'generate_python_code' or 'generate_r_code' beyond the language. It's adequate but lacks specificity about what kind of Stata code it produces.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'generate_python_code' or 'generate_r_code' for language choice, or other code-related tools like 'code_template' or 'optimize_code'. There's no context on prerequisites, scenarios, or exclusions, leaving the agent with minimal usage direction.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'provides' formulas and LaTeX notation, implying a read-only operation, but doesn't clarify aspects like whether it requires authentication, has rate limits, returns structured data, or handles errors. For a tool with no annotation coverage, this leaves significant gaps in understanding its behavior and 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?

The description is extremely concise—a single phrase in Korean that directly states the tool's function without any fluff. It is front-loaded with the core purpose and wastes no words, making it easy for an agent to parse quickly. Every part of the description earns its place by clearly conveying the essential information.

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

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

Given the tool's moderate complexity (2 parameters, no output schema, no annotations), the description is minimally adequate. It covers the basic purpose but lacks details on behavioral traits, usage context, and output expectations. Without annotations or an output schema, the agent must rely heavily on the schema for parameters and guesswork for behavior, leaving room for misinterpretation in operational 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?

The schema description coverage is 100%, with clear descriptions for both parameters: 'concept' (e.g., ols_estimator, did_att) and 'format' (output format as latex, text, or both). The description adds no additional parameter semantics beyond what the schema provides, such as examples of other concepts or details on output formatting. Since the schema does the heavy lifting, the baseline score of 3 is appropriate.

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

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

The description clearly states the tool's purpose: '통계 수식 및 LaTeX 표기법 제공' (provides statistical formulas and LaTeX notation). It specifies both the resource (statistical formulas) and the format (LaTeX notation), making it distinct from most siblings that focus on analysis, code generation, or guidance rather than formula retrieval. However, it doesn't explicitly differentiate from potential formula-related siblings like 'get_method_guide' or 'meta_code', which slightly limits specificity.

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. It doesn't mention any prerequisites, exclusions, or specific contexts for usage. Given the many siblings (e.g., 'search_stats_knowledge', 'get_method_guide', 'code_template'), the lack of differentiation leaves the agent to infer usage based on the name alone, which is insufficient for optimal 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 are provided, so the description carries the full burden of behavioral disclosure. It describes what the tool returns (a detailed guide) but doesn't cover critical aspects like whether it's a read-only operation, if it requires authentication, rate limits, error handling, or the format of the output (e.g., text, structured data). For a tool with no annotation coverage, this is a significant gap.

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 in Korean that front-loads the core purpose. It wastes no words, though it could be slightly more structured by explicitly stating it's a retrieval tool. Every part of the sentence contributes to understanding the tool's function.

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 (2 parameters, no output schema, no annotations), the description is adequate but incomplete. It covers the purpose and parameters indirectly, but lacks details on output format, behavioral traits, and usage context. Without annotations or an output schema, the agent is left guessing about the return value and operational constraints.

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

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

The input schema has 100% description coverage, with clear parameter descriptions and an enum for 'aspect'. The description adds minimal value beyond the schema by listing the aspects (assumptions, procedure, interpretation, reporting) in Korean, which aligns with the enum but doesn't provide additional semantics like examples of method names beyond the schema's examples. Baseline 3 is appropriate when the schema does the heavy lifting.

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

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

The description clearly states the tool's purpose: to retrieve a detailed guide for a specific statistical method, covering aspects like assumptions, procedure, interpretation, and reporting. It uses specific verbs ('get', 'retrieve' implied) and resources ('statistical method guide'), but doesn't explicitly differentiate from siblings like 'bayesian_guide', 'causal_design_guide', or 'sem_guide', which appear to be more specialized guides.

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. It doesn't mention sibling tools like 'compare_methods' for method selection, 'check_assumptions' for assumption validation, or 'suggest_method' for recommendations, leaving the agent with no context for choosing among them.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only states it's a 'guide' for interpretation, but doesn't reveal what the tool actually does behaviorally—e.g., whether it generates text, calculates metrics, requires specific inputs beyond the schema, or has any limitations like handling only certain data types. This lack of detail makes it hard for an agent to predict the tool's behavior or outcomes.

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—a single phrase in Korean that efficiently conveys the core purpose. It's front-loaded with key terms like '회귀계수 해석 가이드' (regression coefficient interpretation guide). However, it could be more structured by explicitly stating the output or action, but its brevity avoids unnecessary fluff, making it easy to parse quickly.

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 statistical interpretation and the lack of annotations and output schema, the description is incomplete. It doesn't specify what the tool returns (e.g., textual explanation, confidence intervals, or visual aids), which is critical for an agent to understand the tool's utility. With 5 parameters and no behavioral context, the description fails to provide enough information for effective tool selection and invocation in a statistical workflow.

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

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

Schema description coverage is 100%, with all parameters well-documented in the schema (e.g., model_type, coefficient, se, variable_type with enums, transformation with enums). The description adds no additional meaning beyond the schema, as it doesn't explain how parameters interact or affect interpretation. Given the high schema coverage, the baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract from the schema's completeness.

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 '회귀계수 해석 가이드 (OLS, Logit, 상호작용 등)' states the general purpose as a guide for interpreting regression coefficients, mentioning specific model types (OLS, Logit) and interactions. However, it's somewhat vague about what the tool actually produces (e.g., textual explanation, visualization, or statistical output) and doesn't clearly differentiate from sibling tools like 'interpret_model_fit' or 'interpret_diagnostics', which could also involve interpretation tasks.

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

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

The description provides no explicit guidance on when to use this tool versus alternatives. It mentions model types (OLS, Logit) and interactions, implying usage for regression analysis, but offers no context on prerequisites, when not to use it, or how it compares to siblings like 'interpret_model_fit'. Without such guidance, users may struggle to select the appropriate tool from the many statistical options available.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'interprets' results, implying a read-only or analytical operation, but doesn't specify whether it modifies data, requires authentication, has rate limits, or describes the output format. For a tool with no annotations, this leaves significant behavioral gaps, though it doesn't contradict any 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 very concise—a single phrase in Korean with examples—and front-loaded with the core purpose. It wastes no words, but it might be overly brief for clarity in some contexts. Every part earns its place by specifying the action and examples, though it could benefit from more structure for non-native speakers.

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 interpreting statistical diagnostics and the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns, how results are formatted, or any behavioral nuances. For a tool with 4 parameters and no output schema, more context is needed to guide effective use, making it inadequate for full understanding.

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

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

Schema description coverage is 100%, so the schema already documents all parameters (test_name, statistic, p_value, context) with descriptions. The tool description adds no additional meaning beyond the schema, such as explaining how parameters interact or providing usage examples. With high schema coverage, the baseline score of 3 is appropriate as the description doesn't compensate but also doesn't detract.

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 as 'interpreting diagnostic results' with specific examples (VIF, DW, BP test), which are statistical diagnostics. It uses a specific verb ('interpret') and resource ('diagnostic results'), making the function unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'interpret_coefficient' or 'interpret_test', which might handle different types of interpretation.

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. It doesn't mention prerequisites, context, or exclusions, nor does it reference sibling tools such as 'interpret_coefficient' or 'interpret_test' that might be relevant for similar tasks. Usage is implied only by the tool name and examples, lacking explicit instructions.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only lists the metrics to be interpreted without explaining what the tool actually does with them (e.g., generates explanations, compares values, provides recommendations). This leaves critical behavioral traits like output format, processing logic, or any limitations undocumented.

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—a single phrase listing the metrics—which is efficient and front-loaded. However, it's arguably too brief, as it doesn't provide enough context for effective use, but within the scope of conciseness, it avoids unnecessary verbosity.

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

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

Given the complexity of interpreting model fit metrics, no annotations, and no output schema, the description is incomplete. It fails to explain what the tool outputs, how it handles different model types, or any prerequisites for use. This leaves significant gaps for an AI agent to understand and invoke the tool correctly in a statistical analysis context.

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

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

Schema description coverage is 100%, so the schema already documents all three parameters (metrics, model_type, comparison). The description doesn't add any meaning beyond what's in the schema—it doesn't clarify what 'metrics' should include, what 'model_type' values are expected, or how 'comparison' affects interpretation. Baseline 3 is appropriate when the schema does the heavy lifting.

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

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

The description clearly states the tool's purpose as interpreting model fit metrics (R², AIC, BIC, Pseudo-R²), which is a specific verb+resource combination. However, it doesn't distinguish itself from sibling tools like 'interpret_coefficient' or 'interpret_diagnostics', which also involve interpretation tasks in statistical analysis.

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

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

The description provides no guidance on when to use this tool versus alternatives. With sibling tools like 'interpret_coefficient' and 'interpret_diagnostics', there's no indication of the specific context or scenarios where this tool is appropriate, leaving the agent to guess based on the tool name alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description reveals nothing about what the tool actually does beyond the tautological statement - no indication of output format, whether it provides natural language interpretation, statistical guidance, or any behavioral characteristics. For a tool with 5 parameters and no annotations, this is completely inadequate.

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?

While technically concise (one short phrase), this represents under-specification rather than effective conciseness. The single phrase doesn't earn its place by providing meaningful information. It's too brief to be helpful, failing to communicate essential details about the tool's function.

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

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

For a tool with 5 parameters, no annotations, no output schema, and multiple sibling alternatives, the description is completely inadequate. It provides no information about what the tool actually produces, how it differs from other interpretation tools, or what behavioral characteristics users should expect. The description fails to compensate for the lack of structured metadata.

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

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

Schema description coverage is 100%, so the schema already documents all 5 parameters with basic descriptions. The tool description adds no additional parameter information beyond what's in the schema. According to scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no parameter information in the description.

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

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

The description '통계 검정 결과 해석' (interpretation of statistical test results) is a tautology that essentially restates the tool name 'interpret_test'. It doesn't specify what kind of interpretation it provides, what format the output takes, or how it differs from sibling tools like 'interpret_coefficient' or 'interpret_model_fit'. The purpose is vague and lacks differentiation from alternatives.

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. With multiple sibling interpretation tools (interpret_coefficient, interpret_diagnostics, interpret_model_fit), there's no indication of what distinguishes this tool's scope or when it's appropriate versus other options. No context, prerequisites, 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 are provided, so the description carries the full burden of behavioral disclosure. It only mentions it's a 'guide' for instrumental variable strength/validity testing, without detailing what the tool actually does (e.g., performs calculations, returns diagnostics, provides recommendations). Critical behavioral traits like output format, computational requirements, or error handling are missing, leaving significant gaps.

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

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

The description is a single phrase, which is concise but under-specified—it doesn't front-load actionable information. While not verbose, it fails to efficiently convey the tool's function, making it less helpful than a more informative yet still brief description would be.

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

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

Given no annotations and no output schema, the description is incomplete for a tool with 3 parameters. It lacks details on what the tool returns, how it behaves, or its practical use, which is insufficient for an AI agent to effectively invoke it. The high schema coverage doesn't compensate for missing behavioral and output context.

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

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

Schema description coverage is 100%, so the schema already documents all parameters (n_instruments, first_stage_f, overid_test). The description adds no additional meaning or context beyond what's in the schema, such as explaining typical values or interactions. Baseline 3 is appropriate as the schema handles parameter documentation 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 '도구변수 강도/유효성 검정 가이드' (Instrumental variable strength/validity test guide) is vague—it states the topic but not the specific action (e.g., 'check', 'calculate', 'evaluate'). It doesn't clearly distinguish this tool from siblings like 'check_assumptions' or 'test_selection', which could overlap in statistical testing contexts. The purpose is implied but lacks a clear verb+resource combination.

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 is provided on when to use this tool versus alternatives. With siblings like 'check_assumptions' and 'test_selection' that might handle similar statistical tests, the description fails to specify context, prerequisites, or exclusions. Usage is only implied by the title, offering no explicit when/when-not instructions.

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 fails to do so—it doesn't indicate if this is a read-only guide, if it modifies data, requires authentication, has rate limits, or what the output format is. For a tool with no annotations, this lack of behavioral information is inadequate.

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, concise phrase in Korean that directly states the tool's topic. It's front-loaded with no wasted words, making it efficient and easy to parse, though it lacks detail.

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

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

Given no annotations and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., a text guide, structured data) or behavioral aspects. For a tool with two parameters and potential complexity in statistical reporting, more context is needed to be fully useful.

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%, with clear descriptions for both parameters (e.g., '목표 저널' for journal, '사용 방법론' for method). The description adds no additional meaning beyond the schema, such as explaining parameter interactions or usage examples. Baseline 3 is appropriate since the schema adequately documents parameters.

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

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

The description '저널별 통계 보고 가이드' (Journal-specific statistical reporting guide) is vague about what the tool actually does. It mentions a guide related to statistical reporting for journals but doesn't specify the action (e.g., generates, provides, explains) or what resource it operates on. While it distinguishes from siblings by mentioning journals, it's too general to clearly understand its function.

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. It doesn't mention prerequisites, context, or compare it to sibling tools like 'get_method_guide' or 'suggest_method', leaving the agent with no usage instructions.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only states it's a 'guide' for marginal effects, implying it provides informational or explanatory content rather than performing computations. However, it fails to disclose key behavioral traits such as whether it generates code, provides textual explanations, requires specific data inputs beyond parameters, or has any side effects. For a tool with no annotation coverage, this leaves significant gaps in understanding how the tool behaves.

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 phrase in Korean that directly addresses the tool's topic. It is appropriately sized for a guide tool, with no wasted words. However, it lacks front-loading of critical information (e.g., what the guide produces), which slightly reduces its effectiveness, but it remains concise.

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

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

Given the complexity of statistical guidance tools and the lack of annotations and output schema, the description is incomplete. It does not specify what the guide outputs (e.g., text, code, examples), its format, or how it integrates with other tools. For a tool with 3 parameters and no structured output information, the description should provide more context about the tool's behavior and results to be sufficiently complete.

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

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

Schema description coverage is 100%, with all parameters (model_type, effect_type, interaction) having descriptions in the schema. The tool description adds no additional meaning about parameters beyond what the schema already provides (e.g., it doesn't explain what 'ame', 'mem', 'mer' stand for or how interaction affects the guide). With high schema coverage, the baseline score is 3, as the description doesn't compensate but also doesn't detract.

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 '한계효과 계산 및 해석 가이드' (Marginal effects calculation and interpretation guide) is a tautology that essentially restates the tool name 'marginal_effects_guide' in Korean. It specifies the general domain (marginal effects) but lacks a clear verb indicating what the tool actually does (e.g., generates, explains, computes). It does not distinguish this tool from potential siblings like 'interpret_coefficient' or 'get_method_guide' that might also relate to statistical interpretation.

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. It does not mention any context, prerequisites, or exclusions. Given the many sibling tools related to statistical methods (e.g., 'interpret_coefficient', 'get_method_guide', 'bayesian_guide'), the absence of usage guidelines leaves the agent guessing about when this specific marginal effects guide is appropriate.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only states what the tool calculates without explaining how it behaves: it doesn't mention output format, error handling, computational limitations, or whether it's a pure calculation versus a data-modifying operation. For a statistical tool with 5 parameters, this leaves significant behavioral gaps.

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

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

The description is extremely concise - a single phrase that efficiently conveys the core purpose. It's front-loaded with the main function. However, the brevity comes at the cost of completeness, as it lacks necessary context for proper tool selection and usage.

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

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

Given the tool's complexity (5 parameters, statistical calculation) and the absence of both annotations and output schema, the description is insufficient. It doesn't explain what the tool returns, how results should be interpreted, or provide context about the statistical methodology. For a specialized calculation tool in a server with many statistical alternatives, more guidance is needed.

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 all parameters are documented in the schema. The description adds no additional parameter information beyond what's in the schema - it doesn't explain relationships between parameters, typical values, or calculation methodology. With complete schema coverage, the baseline score of 3 is appropriate as the description doesn't enhance parameter understanding.

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

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

The description clearly states the tool's purpose: calculating Minimum Detectable Effect (MDE) for A/B testing and experimental design. It specifies the verb 'calculate' and the resource 'MDE', making the function unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'calc_power' or 'calc_sample_size', which are related statistical calculation tools in the same domain.

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. It mentions 'A/B testing, experimental design' as context, but doesn't specify prerequisites, when not to use it, or how it differs from sibling tools like 'calc_power' or 'calc_sample_size' that handle related statistical calculations. The agent must infer usage from the tool name and parameters alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions code generation but doesn't describe output format, error handling, or any behavioral traits like whether it requires specific inputs beyond parameters. This leaves significant gaps in understanding how the tool behaves.

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

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

The description is a single, efficient sentence that directly states the tool's function. It's appropriately sized and front-loaded, with no wasted words, though it could be slightly more informative given the lack of other context.

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

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

Given the complexity of a code-generation tool with 3 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what the generated code looks like, how it's returned, or any dependencies, leaving the agent with insufficient context for effective 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%, so the schema already documents all parameters with descriptions and enums. The description doesn't add any meaning beyond what the schema provides, such as explaining parameter interactions or usage examples, resulting in a baseline score of 3.

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

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

The description states the tool generates code for meta-analysis using specific packages (metafor, meta, metan), which clarifies the verb (generate) and resource (code). However, it doesn't differentiate from sibling tools like 'generate_r_code' or 'generate_stata_code' that might also produce code, making the purpose somewhat vague in 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?

No explicit guidance is provided on when to use this tool versus alternatives. The description implies it's for meta-analysis code generation, but it doesn't specify scenarios, prerequisites, or exclusions compared to other code-related tools in the list.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool performs 'calculation and conversion', implying a read-only operation, but doesn't clarify if it's deterministic, requires specific inputs, handles errors, or produces outputs in a particular format. For a tool with 3 parameters and no annotations, this leaves significant behavioral gaps.

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

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

The description is a single, efficient phrase in Korean that directly states the tool's purpose without unnecessary words. It's appropriately sized for a simple tool, though it could be more structured (e.g., by clarifying the scope). Every word earns its place, but it lacks front-loading of key details like differentiation from siblings.

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 (3 parameters, nested objects, no output schema) and lack of annotations, the description is incomplete. It doesn't explain the output format, error handling, or how parameters interact, leaving the agent to guess. For a calculation tool with multiple input types and no output schema, more context is needed to ensure 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?

Schema description coverage is 100%, so the schema already documents all parameters. The description adds no additional meaning about parameters beyond what's in the schema—it doesn't explain the 'values' object structure, 'target_metric' usage, or provide examples. With high schema coverage, the baseline is 3, as the description doesn't compensate but doesn't detract either.

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 '메타분석용 효과크기 계산 및 변환' (Meta-analysis effect size calculation and conversion) states the general purpose but lacks specificity. It mentions 'effect size' as the resource and 'calculation and conversion' as the verb, but doesn't distinguish it from sibling tools like 'calc_effect_size' or specify what makes it unique for meta-analysis. The purpose is clear but not differentiated from alternatives.

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 is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites, context, or exclusions, and it fails to differentiate from similar tools like 'calc_effect_size' or 'meta_heterogeneity'. Without any usage context, the agent must infer when this tool is appropriate based on the name alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only states the tool's purpose without revealing any behavioral traits: it doesn't specify whether this is a read-only operation, what the output format might be (e.g., textual interpretation, numerical results), error conditions, or computational characteristics (e.g., fast/slow, resource-intensive). For a tool with no annotation coverage, this lack of behavioral context is a significant gap.

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 phrase that front-loads the core purpose without unnecessary words. It uses technical terminology appropriately for its domain (meta-analysis). However, it could be slightly more informative by clarifying the output or usage context, but as-is, it avoids redundancy and 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 the complexity of statistical interpretation and the lack of annotations and output schema, the description is incomplete. It states what the tool does but omits critical context: what the output looks like (e.g., a textual summary, classification of heterogeneity), how results should be used, or any limitations. For a tool with 4 parameters and no structured output information, this leaves too much ambiguity for an agent to invoke it effectively.

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

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

Schema description coverage is 100%, with all parameters (q_stat, i_squared, tau_squared, k) clearly documented in the schema. The description adds no additional parameter semantics beyond what's in the schema—it lists Q, I², τ² in parentheses but doesn't explain their roles, relationships, or interpretation context. Since the schema already fully describes parameters, the baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract.

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 as '메타분석 이질성 해석 (Q, I², τ²)', which translates to 'Meta-analysis heterogeneity interpretation (Q, I², τ²)'. This specifies the verb 'interpret' and the resource 'heterogeneity' with specific statistical measures. It distinguishes from siblings like 'meta_effect_size' or 'meta_code' by focusing on heterogeneity metrics rather than effect sizes or code generation. However, it doesn't explicitly mention what 'interpretation' entails (e.g., providing textual explanations vs. calculations).

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing Q, I², τ² values from prior analysis), when it's appropriate (e.g., after meta-analysis calculations), or what alternatives exist among siblings (e.g., 'meta_effect_size' for different aspects of meta-analysis). The tool name and description imply a niche statistical function, but without explicit usage context, an agent might struggle to apply it correctly.

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 for behavioral disclosure but offers none. It doesn't indicate whether this is a read-only guide, a code generator, an analysis runner, or something else. There's no information about permissions needed, rate limits, output format, or any behavioral characteristics. The description fails to compensate for the complete lack of annotation coverage.

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 - a single phrase with zero wasted words. While this conciseness comes at the cost of completeness, the structure is front-loaded with the core concept. Every element in the description (Korean phrase and method examples) directly relates to the tool's purpose without unnecessary elaboration.

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

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

For a tool with 2 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool actually does (generate code? provide explanations? run analysis?), what users can expect as output, or how to interpret results. The lack of behavioral transparency combined with minimal purpose clarity makes this inadequate for a tool that appears to guide users through complex ML methods for causal inference.

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

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

Schema description coverage is 100%, with both parameters having enum descriptions in Korean ('방법' for method, '추정 대상' for target). The description adds no additional parameter semantics beyond what the schema already provides. It mentions 'Double ML, Causal Forest' which aligns with the method enum values, but doesn't explain parameter relationships, constraints, or usage examples. Baseline 3 is appropriate when 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 '인과추론용 ML 가이드 (Double ML, Causal Forest)' is a tautology that essentially restates the tool name 'ml_for_causal' in Korean with method examples. It doesn't specify what action the tool performs (e.g., generates code, provides explanations, runs analysis) or what resource it operates on. While it mentions specific methods, it doesn't clearly distinguish this tool's function from sibling tools like 'get_method_guide' or 'suggest_method'.

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. There are multiple sibling tools that could potentially overlap with causal ML guidance (e.g., 'get_method_guide', 'suggest_method', 'causal_design_guide'), but the description offers no explicit or implicit context about when this specific tool is appropriate versus those 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 burden. It mentions concepts (ICC, random effects, cross-level interactions) but doesn't disclose behavioral traits like output format (e.g., text, code, visualization), interactivity, or prerequisites (e.g., data input). This leaves the agent guessing about how the tool behaves when invoked.

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

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

The description is concise with a single phrase listing key concepts, which is efficient and front-loaded. However, it could be more structured by clarifying the tool's action (e.g., 'Generate guidance for...') to improve 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?

Given no annotations, no output schema, and a tool with 3 parameters (one required), the description is incomplete. It doesn't explain what the tool returns (e.g., explanations, code snippets, recommendations) or how parameters affect the output, leaving significant gaps for the agent to understand the tool's functionality.

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

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

Schema description coverage is 100%, so the schema already documents all parameters (levels, random_effects, cross_level). The description doesn't add meaning beyond what the schema provides, such as explaining how parameters influence the guidance or providing examples. Baseline 3 is appropriate when schema does the heavy lifting.

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

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

The description states the tool provides guidance for multilevel modeling concepts (ICC, random effects, cross-level interactions), which gives a general purpose. However, it's vague about what specific guidance it offers (e.g., interpretation, implementation, selection) and doesn't distinguish from siblings like 'sem_guide' or 'bayesian_guide' that also provide statistical guidance.

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 is provided. The description implies it's for multilevel modeling contexts, but it doesn't specify scenarios (e.g., planning, analysis, reporting) or compare to siblings like 'get_method_guide' or 'suggest_method'. Usage is only loosely inferred from the topic.

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 'suggestions' which implies advisory/non-destructive output, but doesn't clarify if it modifies code, requires specific inputs beyond parameters, has rate limits, or what the output format looks like. For a tool with no annotation coverage, this leaves significant behavioral gaps.

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

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

The description is a single, efficient sentence in Korean that directly states the tool's purpose. It's front-loaded with no wasted words, making it easy to parse despite language differences. Every part of the sentence contributes meaning.

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

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

Given no annotations and no output schema, the description is incomplete for a tool with 3 parameters. It doesn't explain what kind of suggestions are provided, how they're formatted, or any behavioral constraints. For a code optimization tool in a research/statistics context (per siblings), more context about output expectations is needed.

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 parameters are well-documented in the schema itself. The description adds no additional parameter semantics beyond implying optimization is for 'large-scale data' (hinting at data_size relevance). With high schema coverage, baseline 3 is appropriate as the description doesn't compensate but doesn't need to heavily.

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 as 'code optimization suggestions for large-scale data' (verb+resource+scope). It distinguishes from siblings like debug_code (fixing errors) or code_template (creating templates) by focusing on performance optimization. However, it doesn't explicitly differentiate from all possible optimization-related siblings, keeping it at 4 rather than 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 guidance on when to use this tool versus alternatives. With many sibling tools (e.g., debug_code, generate_python_code, suggest_method), there's no indication of when optimization is preferred over other code-related actions. The description only states what it does, not when it's appropriate.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description reveals nothing about what the tool actually does behaviorally—whether it's a read-only guide, a code generator, a statistical calculator, or something else. It doesn't mention permissions, side effects, output format, or any behavioral traits. This is inadequate for a tool with no annotation coverage.

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 Korean phrase that's under-specified rather than concise. While brief, it fails to convey essential information about the tool's purpose or behavior. Every sentence should earn its place, but this description doesn't provide enough substance to justify its existence as a helpful tool description.

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 statistical testing tools and the complete lack of annotations and output schema, the description is severely incomplete. It doesn't explain what the tool returns, how it behaves, or what users can expect. For a tool that presumably performs or guides through parallel trends testing (a non-trivial statistical concept), this minimal description fails to provide the necessary context for effective 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%, with both parameters ('pre_periods' and 'approach') having descriptions in the schema. The tool description adds no additional meaning about parameters beyond what's already documented in the schema. According to the rules, when schema coverage is high (>80%), the baseline score is 3 even with no parameter information in the description.

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

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

The description 'DID 평행추세 검정 가이드' (DID parallel trends test guide) is a tautology that essentially restates the tool name 'parallel_trends_check' in Korean with 'guide' added. It doesn't specify what the tool actually does (e.g., whether it performs the test, explains the methodology, or generates code). While it mentions DID (Difference-in-Differences), it doesn't distinguish this tool from sibling tools like 'event_study_guide' or 'check_assumptions' that might cover related concepts.

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. It doesn't mention any context, prerequisites, or exclusions for using this tool. With many sibling tools related to causal inference and statistical methods (e.g., 'causal_design_guide', 'check_assumptions', 'event_study_guide'), users are left guessing about when this specific parallel trends check is appropriate.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. While '데이터 생성' (data generation) implies a creation operation, the description doesn't specify whether this is a read-only calculation, a write operation that stores data, what format the output takes, or any performance characteristics. For a statistical tool with no annotation coverage, this leaves significant behavioral gaps.

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

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

The description is extremely concise - a single phrase that directly states the tool's purpose. There's no wasted language, repetition, or unnecessary elaboration. It's front-loaded with the core functionality and includes the specific application (for visualization).

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 statistical calculation tool with 4 parameters and no output schema, the description is insufficient. It doesn't explain what the tool returns (data format, structure), how the power curve is calculated, or what visualization it's preparing data for. With no annotations and no output schema, the description should provide more context about the tool's behavior and outputs.

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

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

The schema has 100% description coverage, so all parameters are documented in the schema itself. The description doesn't add any parameter-specific information beyond what's already in the schema descriptions. According to the scoring rules, when schema_description_coverage is high (>80%), the baseline is 3 even with no parameter information in the description.

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

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

The description clearly states the tool's purpose: '검정력 곡선 데이터 생성 (시각화용)' translates to 'Power curve data generation (for visualization)'. This specifies both the action (data generation) and the resource (power curve), and distinguishes it from sibling tools like 'calc_power' or 'visualization_code' by focusing specifically on curve data generation rather than calculation or general visualization.

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. It doesn't mention when this tool is appropriate, what prerequisites might be needed, or how it differs from similar tools like 'calc_power' or 'visualization_code'. The agent must infer usage from the name and description alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool creates templates but does not describe what 'create' entails—e.g., whether it generates a file, returns structured data, requires authentication, or has side effects. For a creation tool with zero annotation coverage, this is a significant gap in transparency about its behavior and implications.

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—a single phrase in Korean that directly states the tool's function and target platforms. It is front-loaded with the core purpose and wastes no words, making it efficient for quick understanding without unnecessary detail.

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

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

Given the complexity of a template creation tool with no annotations and no output schema, the description is incomplete. It does not explain what the tool outputs (e.g., a template file, JSON structure), any behavioral traits like error handling, or usage context. For a tool that likely generates structured content, more information is needed to guide the agent effectively.

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

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

Schema description coverage is 100%, with all parameters documented in the schema (platform, study_type, hypotheses). The description does not add any meaning beyond this, such as explaining the purpose of each parameter or providing examples. Since the schema fully covers the parameters, the baseline score of 3 is appropriate, as the description neither compensates nor adds value beyond the structured data.

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: '사전등록 템플릿 생성' (create preregistration template) and specifies the target platforms (OSF, AsPredicted). It uses a specific verb ('생성' - create) and identifies the resource (template). However, it does not explicitly differentiate from sibling tools, which include various research-related utilities like 'create_project_structure' or 'code_template', leaving some ambiguity about its unique role.

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. It does not mention any prerequisites, context for use (e.g., during study planning), or exclusions. With many sibling tools for research tasks, the lack of usage context leaves the agent without clear direction on selecting this tool appropriately.

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 for behavioral disclosure but provides none. It doesn't indicate whether this is a read-only informational guide, an interactive calculator, a code generator, or something else. It doesn't mention permissions needed, rate limits, side effects, or what kind of output to expect. The three Korean terms in parentheses are too vague to constitute meaningful behavioral information.

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 (just 7 Korean characters plus 3 terms in parentheses), but this brevity comes at the cost of being under-specified rather than efficiently informative. While it's not verbose or repetitive, it fails to provide the essential information needed to understand the tool's function and use.

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 implied by the tool name (propensity score matching is a sophisticated statistical technique), the lack of annotations, and no output schema, the description is completely inadequate. It doesn't explain what the tool produces, how it should be used, what knowledge domain it addresses, or how it differs from related tools. For a statistical guidance tool with parameters, this minimal description leaves the agent guessing about fundamental aspects of the tool's operation.

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 doesn't add any meaningful parameter information beyond what's already in the schema - it mentions 'matching' and 'balance check' which correspond to the two parameters, but provides no additional context about parameter selection, dependencies, or practical implications. The description doesn't compensate for any gaps since there are none in the schema documentation.

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 '성향점수매칭 가이드 (추정, 매칭, 균형검정)' translates to 'Propensity Score Matching Guide (estimation, matching, balance check)' which is somewhat tautological - it restates the tool name 'psm_guide' and adds three Korean terms that are essentially synonyms or components of PSM. While it hints at the domain (propensity score matching), it doesn't specify what action the tool performs (e.g., 'generate', 'calculate', 'evaluate', 'implement') or what resource it operates on.

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 the many sibling tools on the server. With 50+ sibling tools including various statistical guides (bayesian_guide, causal_design_guide, event_study_guide, etc.), there's no indication of when this PSM guide is appropriate versus alternatives like 'suggest_method' or 'compare_methods' or other causal inference 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 carries the full burden of behavioral disclosure. '가이드' (guide) suggests it might provide instructions or recommendations rather than perform computations, but this is ambiguous—it could output text, code, or statistical results. The description doesn't clarify if it's read-only, requires specific inputs beyond the schema, has side effects, or details output format (e.g., textual guide vs. statistical report). For a tool with no annotations, this lack of behavioral context is a significant gap.

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 phrase '출판편향 검정 가이드', which is concise and front-loaded with the core purpose. There's no wasted text or redundancy. However, it's overly brief for a tool with parameters and potential complexity, bordering on under-specification rather than optimal conciseness, but it efficiently communicates the essence without fluff.

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

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

Given the tool has 2 parameters, no annotations, and no output schema, the description is incomplete. It doesn't address what the tool outputs (e.g., a guide text, statistical results, or code), behavioral aspects like whether it performs calculations or provides instructions, or how it integrates with sibling tools. For a statistical testing tool in a server with many analytical siblings, more context is needed to understand its role and 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?

Schema description coverage is 100%, with clear descriptions for both parameters: 'methods' as an array of strings for test methods (funnel_plot, egger, trim_fill, selection_model) and 'k' as a number for study count. The description adds no additional meaning beyond the schema, such as explaining method differences or typical 'k' values. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, but there's no compensation for potential gaps like method selection guidance.

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 '출판편향 검정 가이드' (Publication bias testing guide) states the general purpose as a guide for publication bias testing, which is clear but vague. It specifies the domain (publication bias) and action (testing/guide), but lacks a specific verb-resource combination like 'perform publication bias tests' or 'guide through publication bias analysis methods'. It doesn't distinguish from siblings like 'meta_heterogeneity' or 'test_selection', which might cover related statistical concepts.

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. It doesn't mention contexts like meta-analysis, statistical validation, or comparison with other tools (e.g., 'meta_heterogeneity' for heterogeneity testing or 'test_selection' for general testing). There's no indication of prerequisites, scenarios, or exclusions, leaving usage entirely implicit based on the tool name alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. However, it only states it's a 'guide' without explaining what that entails—e.g., whether it performs calculations, returns recommendations, requires specific inputs beyond the schema, or has any side effects like data processing. This is inadequate for a tool with parameters and no output schema.

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

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

The description is a single phrase ('RDD 대역폭 선택 가이드') that is overly concise to the point of under-specification. It lacks any structure or elaboration to clarify the tool's purpose or usage, making it inefficient for an agent to understand without additional context. This is not true conciseness but rather omission of necessary details.

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

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

Given the tool has 2 parameters, no annotations, and no output schema, the description is incomplete. It fails to explain what the tool does, how it behaves, or what it returns, leaving significant gaps for an agent to invoke it correctly. Compared to siblings like 'calc_effect_size' or 'suggest_method', this description provides minimal contextual value.

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

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

The input schema has 100% description coverage, with clear enum values and descriptions for both parameters ('design' and 'method'). The description adds no additional meaning beyond the schema, such as explaining how these parameters interact or what 'RDD 유형' (RDD type) entails. Since schema coverage is high, the baseline score of 3 is appropriate.

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

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

The description 'RDD 대역폭 선택 가이드' (RDD bandwidth selection guide) is tautological—it essentially restates the tool name 'rdd_bandwidth' in Korean without specifying what the tool actually does (e.g., whether it calculates, recommends, or visualizes bandwidth). It does not distinguish this tool from its many siblings, which include various statistical and coding tools like 'calc_effect_size' or 'suggest_method'.

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. It does not mention any context, prerequisites, or exclusions, nor does it reference sibling tools like 'compare_methods' or 'suggest_method' that might be related. This leaves the agent with no information to decide when this tool is appropriate.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only hints at providing guidance on structure but doesn't specify if this tool generates files, outputs text, requires specific inputs beyond the schema, or has any side effects (e.g., file creation). For a tool with no annotation coverage, this lack of detail on behavior is a significant gap, leaving the agent uncertain about what the tool actually does beyond its inputs.

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

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

The description is a single, efficient phrase ('재현성 패키지 구조 가이드') that is front-loaded and wastes no words. However, it's overly concise to the point of under-specification, lacking necessary detail for clarity. While structurally sound, it could benefit from additional context to improve usefulness without becoming verbose.

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

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

Given the complexity implied by the tool name and sibling tools, the description is incomplete. With no annotations and no output schema, the description doesn't explain what the tool returns (e.g., a guide document, structured output, or file paths) or its behavioral traits. For a tool that likely involves guidance generation, this leaves critical gaps in understanding how to use it effectively in context.

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

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

The input schema has 100% description coverage, with clear documentation for 'journal' (target journal) and 'components' (included elements like code, data). The description doesn't add any meaning beyond this—it doesn't explain parameter interactions, provide examples, or clarify semantics. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, as the description neither compensates nor detracts from the schema's information.

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

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

The description '재현성 패키지 구조 가이드' (Replication package structure guide) is vague—it suggests guidance on structure but lacks a specific verb and resource. It doesn't clearly state what the tool does (e.g., generates, validates, or explains a replication package), and it fails to distinguish from siblings like 'create_project_structure' or 'code_template', which might overlap in purpose. This is closer to a tautology of the tool name than a clear functional statement.

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 is provided on when to use this tool versus alternatives. The description doesn't mention context, prerequisites, or exclusions, and it doesn't reference sibling tools (e.g., 'create_project_structure' for general project setup or 'journal_guide' for journal-specific requirements). Without this, an agent must infer usage from the tool name alone, which is insufficient for effective selection.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. However, it offers no information on what the tool does (e.g., generates text, analyzes data, provides recommendations), its output format, permissions needed, or any side effects. This is inadequate for a tool with parameters and no output schema.

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

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

The description is a single phrase that is under-specified rather than concise—it fails to convey essential information. While it is brief, it lacks structure and front-loading of key details, making it inefficient for agent understanding.

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 implied by parameters (e.g., statistical critique types) and the lack of annotations and output schema, the description is incomplete. It does not explain what the tool produces, how it behaves, or its role among sibling tools, leaving significant gaps for agent invocation.

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

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

Schema description coverage is 100%, so the schema already documents all parameters (critique_type, current_method, data_constraints) with descriptions and enums. The description adds no additional meaning, syntax, or examples beyond what the schema provides, meeting the baseline score of 3 for 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 '리뷰어 통계 지적 대응 가이드' (Reviewer Statistical Critique Response Guide) is vague and tautological—it restates the tool's name 'reviewer_response' without specifying what it actually does. It lacks a clear verb (e.g., 'generate', 'provide', 'analyze') and resource (e.g., 'responses', 'guidance', 'solutions'), making it unclear how this differs from siblings like 'robustness_guide' or 'suggest_method'.

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 is provided on when to use this tool versus alternatives. The description does not mention context, prerequisites, or exclusions, and it fails to differentiate from sibling tools such as 'robustness_guide' or 'check_assumptions', which might handle similar statistical critiques. This leaves the agent with no basis for selection.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states it's a guide for robustness testing with alternative models and sensitivity analysis, but doesn't reveal if it's informational, interactive, requires specific inputs beyond parameters, or has any behavioral traits like rate limits, permissions, or output format. This leaves significant gaps in understanding how the tool behaves.

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 phrase in Korean that front-loads the key terms. It's appropriately sized for a guide tool, with no wasted words, though it could be more structured if it included brief functional details.

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

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

Given no annotations, no output schema, and a tool with 2 parameters, the description is incomplete. It doesn't explain what the guide produces (e.g., text, code, recommendations), how it interacts with inputs, or any behavioral aspects. For a tool that might involve complex statistical guidance, this leaves too much ambiguity for effective 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%, with parameters 'main_analysis' and 'concerns' fully described in the schema. The description doesn't add any meaning beyond this, such as examples or contextual usage of parameters. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, but no extra value is provided.

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

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

The description '강건성 검정 가이드 (대안모형, 민감도분석)' translates to 'Robustness test guide (alternative models, sensitivity analysis)', which indicates a guide for robustness testing with specific techniques mentioned. However, it's vague about what the tool actually does (e.g., generates guidance, explains methods, or performs analysis) and doesn't clearly distinguish from siblings like 'check_assumptions' or 'compare_methods' that might overlap in statistical validation contexts.

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 is provided on when to use this tool versus alternatives. The description lists techniques but doesn't specify contexts, prerequisites, or exclusions. Given siblings like 'check_assumptions' or 'compare_methods', users might be uncertain about when this guide is the appropriate choice for robustness-related tasks.

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 for behavioral disclosure. It mentions the tool provides '방법론, 가정, 해석 가이드' which gives some context about output content, but doesn't describe the search behavior (e.g., is it semantic search? keyword-based?), result format, limitations, or any operational constraints. For a search tool with zero annotation coverage, this leaves significant behavioral gaps.

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

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

The description is appropriately concise with two clear phrases that efficiently convey the core functionality. It's front-loaded with the main purpose ('통계/계량경제학 지식베이스 RAG 검색') followed by the value proposition. No wasted words, though it could benefit from slightly more structure.

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 (knowledge search with filtering), lack of annotations, and no output schema, the description is insufficiently complete. It doesn't explain what the search returns (snippets? full documents? citations?), how results are ranked, what the knowledge base contains, or any limitations. For a search tool in a domain-specific context, this leaves too many unanswered questions.

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

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

Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema. The baseline score of 3 is appropriate when the schema does the heavy lifting, though the description could have explained parameter interactions or provided examples.

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

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

The description clearly states the tool's purpose: '통계/계량경제학 지식베이스 RAG 검색' (statistics/econometrics knowledge base RAG search) and specifies it provides '방법론, 가정, 해석 가이드' (methodology, assumptions, interpretation guides). It distinguishes from siblings by focusing on knowledge retrieval rather than calculation, analysis, or code generation tools. However, it doesn't explicitly differentiate from potential similar search tools (none appear 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 provides no guidance on when to use this tool versus alternatives. While the purpose suggests it's for retrieving methodological knowledge, there's no mention of when to choose this over other knowledge-focused tools like 'get_method_guide' or 'suggest_method' from the sibling list. No exclusions, prerequisites, or contextual boundaries are provided.

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

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

No annotations are provided, so the description must fully disclose behavioral traits. However, it only names the tool and its components without explaining what the tool does (e.g., whether it generates code, provides explanations, or performs calculations), its output format, any side effects, or operational constraints like rate limits. This lack of information makes it impossible for an agent to understand the tool's behavior.

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

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

The description is concise with a single phrase, but it is not front-loaded with actionable information. It wastes space by repeating the tool name and adding vague parenthetical terms without clarifying the tool's function. While brief, it fails to convey essential details efficiently, making it under-specified rather than optimally concise.

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

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

Given the complexity of SEM tools, no annotations, no output schema, and a vague description, this is highly incomplete. The description does not explain what the tool produces (e.g., a guide document, code, analysis), how to interpret results, or any dependencies. It leaves critical gaps for an agent to use the tool effectively, especially compared to more detailed sibling tools.

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

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

The input schema has 100% description coverage, with parameters 'model_type' (with enum values) and 'fit_indices' documented in the schema. The description adds no meaning beyond this, as it does not mention parameters at all. According to the rules, with high schema coverage (>80%), the baseline score is 3 when no parameter info is provided in the description.

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

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

The description '구조방정식모형 가이드 (측정모형, 구조모형)' translates to 'Structural Equation Modeling Guide (Measurement Model, Structural Model)', which restates the tool name 'sem_guide' in Korean and adds parenthetical terms that are essentially synonyms or components of SEM. It does not specify a clear action (e.g., 'generate', 'explain', 'analyze') or distinguish this tool from siblings like 'mlm_guide' or 'timeseries_guide'. This is a tautology with minimal added value.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention any context, prerequisites, or comparisons to sibling tools such as 'get_method_guide' or 'suggest_method', which might offer overlapping functionality. There is no explicit or implied usage advice, leaving the agent without direction.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool '추천' (recommends) methods, which implies a read-only, advisory function, but does not detail output format, limitations, or potential side effects. For a tool with 4 parameters and no output schema, this lack of behavioral context is a significant gap, as the agent cannot anticipate what the recommendation will entail.

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, concise sentence in Korean: '연구질문과 데이터 특성에 맞는 통계 방법 추천'. It is front-loaded and wastes no words, efficiently conveying the core purpose without redundancy. Every part of the sentence contributes directly to understanding the tool's function.

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 statistical method recommendation, the description is incomplete. It lacks details on output (no output schema provided), behavioral traits, and usage context. With no annotations and many sibling tools, the description does not provide enough information for an AI agent to fully understand how to invoke or interpret results, making it inadequate for the tool's intended function.

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

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

The input schema has 100% description coverage, with clear enum values and descriptions for parameters like 'dv_type' and 'data_structure'. The description adds no additional semantic information beyond the schema, such as examples or usage tips. With high schema coverage, the baseline score is 3, as the schema adequately documents parameters without extra help from the description.

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

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

The description clearly states the tool's purpose: '연구질문과 데이터 특성에 맞는 통계 방법 추천' (Recommend statistical methods suitable for research questions and data characteristics). It specifies the verb '추천' (recommend) and the resource '통계 방법' (statistical methods), making the intent unambiguous. However, it does not explicitly differentiate from sibling tools like 'compare_methods' or 'test_selection', which might offer similar functionality, so it falls short of a perfect score.

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. With many sibling tools related to statistical methods (e.g., 'compare_methods', 'test_selection', 'get_method_guide'), there is no indication of context, prerequisites, or exclusions. Usage is implied by the tool's name and description but not explicitly stated, leaving gaps for an AI agent to infer correctly.

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 '결과표 생성 코드' (result table generation code), which implies a read-only code generation operation, but doesn't clarify if it creates files, outputs text, or has side effects like modifying data. There's no information on permissions, rate limits, or error handling. The description adds minimal behavioral context beyond the basic action, failing to compensate for the lack of 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 a single, efficient phrase in Korean, listing key libraries without unnecessary words. It's front-loaded with the core purpose. However, it could be more structured by explicitly stating the action (e.g., 'Generate code for statistical tables in R, Stata, or Python'). The brevity is appropriate but slightly under-specified for clarity.

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

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

Given the complexity (3 parameters with enums, no output schema, no annotations), the description is incomplete. It doesn't explain the tool's output (e.g., code snippets, file paths), behavioral aspects, or how it differs from siblings. For a code generation tool with specific parameter constraints, more context is needed to guide the agent effectively, such as example use cases or output format details.

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

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

The input schema has 100% description coverage with clear enums for table_type, format, and language, documenting all parameters. The description adds no parameter semantics beyond what the schema provides—it doesn't explain what 'descriptive' vs. 'regression' tables entail or how the libraries map to languages. With high schema coverage, the baseline is 3, as the description doesn't enhance parameter understanding but doesn't detract either.

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 '결과표 생성 코드 (stargazer, esttab, pandas)' is in Korean and translates to 'result table generation code (stargazer, esttab, pandas)'. It states the tool generates code for result tables using specific libraries, which gives a basic purpose. However, it's vague about what 'result tables' entail (e.g., statistical tables, data summaries) and doesn't differentiate from siblings like 'visualization_code' or 'code_template', which might also involve code generation. The title is null, so the description carries the full burden but only provides a general concept without specific verb+resource 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 provides no guidance on when to use this tool versus alternatives. It lists library names (stargazer, esttab, pandas) which imply usage for R, Stata, and Python code generation, but doesn't specify contexts like 'use for academic paper tables' or 'prefer over visualization_code for tabular outputs'. With many sibling tools like 'generate_python_code' or 'write_results_section', there's no explicit or implied differentiation, leaving the agent to guess based on parameter enums alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description reveals nothing about what the tool actually does behaviorally—whether it generates recommendations, evaluates inputs, returns explanations, or performs calculations. It doesn't mention permissions, rate limits, or output format, leaving the agent completely in the dark about the tool's operation.

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—a single Korean phrase—with zero wasted words. However, this brevity comes at the cost of being under-specified rather than efficiently informative, slightly reducing its effectiveness as a standalone description.

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 implied by 3 parameters (including nested objects) and no annotations or output schema, the description is incomplete. It doesn't explain what the tool outputs (recommendations, explanations, code?) or how it behaves, making it inadequate for an agent to understand the tool's role among many statistical siblings.

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

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

Schema description coverage is 100%, with all parameters documented in the schema itself (purpose with enum values, variable_types, sample_characteristics). The description adds no additional meaning about parameters beyond what's already in the structured schema, so it meets the baseline of 3 where 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 '적절한 통계 검정 선택 가이드' (appropriate statistical test selection guide) is a tautology that essentially restates the tool name 'test_selection' in Korean. It doesn't specify what action the tool performs (does it recommend, evaluate, or generate something?) or what resource it acts upon. Compared to siblings like 'suggest_method' or 'compare_methods', it lacks differentiation.

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

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

The description provides no guidance on when to use this tool versus alternatives. Given siblings like 'suggest_method', 'compare_methods', and 'get_method_guide' that might overlap in function, there's no indication of this tool's specific context, prerequisites, or exclusions. The agent must infer usage from parameters alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only states what the tool is about, not how it behaves: it doesn't specify whether this generates code, provides explanations, returns structured guidance, or has any limitations. For a guidance tool with zero annotation coverage, this is a significant gap in 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 - a single phrase listing the tool's focus areas. Every word earns its place by specifying the analytical domain and key methods. There's no wasted verbiage or unnecessary elaboration.

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 guidance tool with no annotations and no output schema, the description is insufficiently complete. It doesn't indicate what form the guidance takes (text, code examples, structured advice), what depth it provides, or what users can expect as output. The context signals show this is a 2-parameter tool with method selection, but the description doesn't help users understand what they'll receive.

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

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

Schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description doesn't add any meaning beyond what's in the schema - it doesn't explain what 'analysis' choices mean in practice or how 'stationarity' affects the guidance. With complete schema coverage, the 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's purpose: providing guidance for time series analysis with specific methods listed (ARIMA, VAR, cointegration). It uses a specific verb ('guide') and identifies the resource domain (time series analysis). However, it doesn't explicitly differentiate from sibling tools like 'get_method_guide' or 'suggest_method' that might also provide methodological guidance.

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. It doesn't mention prerequisites, appropriate contexts, or when other tools like 'get_method_guide' or 'suggest_method' might be more suitable. The user must infer usage from the title alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does (generates visualization code) but doesn't describe what the output looks like (code snippets? complete scripts?), whether it requires specific data formats as input, what happens with the customization parameter, or any limitations. For a code generation tool with zero annotation coverage, this is a significant gap in behavioral context.

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

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

The description is extremely concise - a single phrase in parentheses that efficiently communicates the scope. Every word earns its place by specifying the visualization libraries supported. There's no wasted text, repetition, or unnecessary elaboration. The structure is front-loaded with the core purpose immediately 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?

For a code generation tool with 3 parameters (including a nested object for customization) and no output schema, the description is insufficient. It doesn't explain what the tool outputs (code format, completeness), how the customization parameter works, or provide examples. With no annotations and rich parameter structure, the description should do more to help an agent understand how to use this tool effectively.

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

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

Schema description coverage is 100%, so the schema already documents all three parameters with descriptions and enums. The description doesn't add any parameter-specific information beyond what's in the schema. It mentions the three libraries (ggplot2, matplotlib, Stata graphs) which correspond to the language enum values, but this doesn't provide additional semantic value beyond the schema. Baseline 3 is appropriate when 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 states the tool's purpose: '시각화 코드 생성' (visualization code generation) with specific libraries mentioned (ggplot2, matplotlib, Stata graphs). It distinguishes from siblings like generate_python_code or generate_r_code by focusing specifically on visualization code rather than general code generation. However, it doesn't explicitly differentiate from table_code or other visualization-related tools.

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

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

The description provides no guidance on when to use this tool versus alternatives. There are many sibling tools that could overlap (generate_python_code, generate_r_code, table_code, power_curve, etc.), but the description offers no explicit when/when-not guidance or mentions of prerequisites. The user must infer usage from the tool name and description alone.

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 for behavioral disclosure. While '저장' (save) implies a write operation, it doesn't specify file system permissions needed, whether files are overwritten or appended, error conditions, or what happens if the directory doesn't exist. For a file-writing tool with zero annotation coverage, this represents significant behavioral gaps.

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

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

The description is a single, efficient phrase that communicates the core purpose without unnecessary words. It's appropriately sized for a straightforward file-writing tool and gets directly to the point with zero wasted verbiage.

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 file-writing tool with no annotations and no output schema, the description is insufficient. It doesn't address critical context like file overwrite behavior, permission requirements, error handling, or what constitutes successful completion. Given the potential complexity of file system operations, more behavioral context is needed.

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

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

Schema description coverage is 100%, so the schema already documents all four parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema, nor does it explain relationships between parameters. This meets the baseline expectation when 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 '분석 코드/결과를 파일로 저장' clearly states the tool's purpose as saving analysis code/results to a file, using a specific verb ('저장' - save) and resource ('파일' - file). However, it doesn't explicitly differentiate from sibling tools like 'write_results_section' or 'replication_package' which might also involve file writing operations, preventing a perfect score.

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. With many sibling tools that might involve file operations or analysis output, there's no indication of this tool's specific context, prerequisites, or when other tools would be more appropriate.

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 the tool creates a template, implying a write operation, but does not disclose behavioral traits like whether it modifies existing data, requires specific permissions, or has rate limits. The description is too vague to provide adequate transparency for a tool with potential mutation 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 a single, concise sentence in Korean, which is efficient. However, it is under-specified rather than truly concise, as it lacks necessary details for clarity and usage. The structure is front-loaded but incomplete, earning a middle score for brevity without sufficient content.

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

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

Given no annotations, no output schema, and a tool that likely involves creating content (implying mutation), the description is incomplete. It does not explain what the tool outputs (e.g., a text template, file path) or provide context on its role among sibling tools. For a 3-parameter tool with nested objects, more detail is needed to guide effective 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%, so the schema already documents all parameters (analysis_type, results, style) with descriptions. The tool description does not add any meaning beyond the schema, such as explaining the purpose of 'results' as an object or the context for style choices. Baseline 3 is appropriate as the schema handles parameter documentation 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 '결과 섹션 작성 템플릿 생성' (creates a results section writing template) restates the tool name 'write_results_section' in Korean, making it tautological. It specifies creating a template for a results section but does not clarify what type of results (e.g., statistical, research) or distinguish it from sibling tools like 'apa_reporting' or 'table_code' that might involve similar reporting tasks.

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

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

There is no guidance on when to use this tool versus alternatives. The description does not mention any context, prerequisites, or exclusions, and it fails to reference sibling tools that might be related, such as 'apa_reporting' or 'journal_guide', leaving the agent without usage direction.

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