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

With no annotations, the description carries full burden. It discloses the source (대학알리미) and comparison criteria, but does not explain behavioral aspects like handling missing data, output format, or what happens when majorName is omitted.

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?

Single sentence with parenthetical source note, no redundancy. Each element is essential and contributes to 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 no output schema, the description does not explain return values or format. It covers the core purpose but omits details on output structure or limitations, especially regarding the optional majorName parameter.

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

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

Schema covers 50% (universities described as 2~4 universities). Description adds meaning by indicating the comparison is for the same department across universities, clarifying the role of majorName, which is otherwise undocumented.

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

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

Description clearly states the tool compares multiple universities by competition rate, tuition, scholarships, and employment rate, and evaluates cost-effectiveness. It distinguishes from sibling tools like search_university or get_major by specifying the comparison 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?

Description implies usage for comparing universities on given metrics but provides no explicit guidance on when to use this tool over alternatives, nor exclusions. It lacks when-to-use/when-not-to-use context.

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

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

No annotations are present, so the description bears full responsibility for disclosing behavioral traits. It only mentions that the tool generates drafts and is supplementary, but does not disclose whether it modifies any data, requires specific permissions, or has rate limits. The word 'draft' hints at non-finality, but this is insufficient for safe invocation.

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

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

The description is two concise sentences that effectively communicate the core functionality and usage context. It is front-loaded with the primary action, and every word is meaningful with no redundancy.

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

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

Given the presence of 6 parameters (2 required), no output schema, and no annotations, the description is too brief. It does not explain the return format, the relationship between inputs and outputs, or any prerequisites. Teachers are told to refine drafts, but agents lack guidance on expected behavior.

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

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

Schema description coverage is only 17% (only 'tone' has a description). The tool description does not explain the role of parameters like studentName, interests, scoreBand, or candidateUniversities. While parameter names are somewhat self-explanatory, the description adds no extra semantic guidance beyond what can be inferred from names.

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

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

The description clearly states the tool generates drafts of college counseling comments, parent notices, and application reason statements based on collected information. It uses specific verbs ('generates') and resources ('drafts'), and distinguishes from sibling tools (which focus on exploration, matching, and search).

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

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

The description implies the tool is for teachers to create drafts that they later refine, but it does not explicitly state when to use this tool versus alternatives (e.g., compare, search_major). No direct comparison or exclusionary guidance is provided.

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

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

No annotations exist, so the description must disclose behavioral traits. It only mentions the source (CareerNet) and what is shown, but not whether the operation is read-only, requires authentication, or any side effects.

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

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

The description is a single concise sentence that front-loads the main function. No unnecessary words.

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

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

Given only one required parameter and no output schema, the description sufficiently covers the tool's purpose and data source. It lacks some details like output format but is adequate for a simple lookup tool.

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

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

Schema coverage is 100% with a clear description for jobName. The tool description adds no extra meaning beyond the schema, so baseline 3 is appropriate.

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

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

The description clearly states the tool shows job details: work, salary, prospects, and how to become one. It is specific and distinguishes from siblings by focusing on a single job's details, not comparisons or other 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?

No explicit usage guidelines are provided; it does not mention when to use this tool versus alternatives like compare or portfolio, nor when not to use it.

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

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

No annotations provided, so description carries full burden. It discloses the type of information shown and the data source (CareerNet, University Alimi). However, it does not mention read-only nature, data freshness, authentication requirements, or potential response size. Basic transparency but could be more thorough.

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

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

Description is a single sentence with a source attribution, perfectly concise and front-loaded. Every word serves a purpose.

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

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

For a simple detail tool with one parameter and no output schema, the description adequately covers what the tool does and the data source. It could be more complete by noting that data may not be real-time or any prerequisites, but overall it's sufficient for an agent to understand the tool's purpose.

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 already describes the single parameter 'majorName' with an example ('물리치료학과'). Description adds no additional semantic meaning beyond that. Since schema coverage is 100%, 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?

Description clearly states the tool shows curriculum, career fields, related jobs, and employment rate for a specific department. It uses a specific verb ('shows') and resource ('one department'), and is distinct from sibling tools like search_major (searching/listings) and compare (comparison).

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

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

Usage is implied: use when needing detailed information about a specific major. However, no explicit when-to-use or when-not-to-use guidance is given, nor are alternatives like search_major or explore_job mentioned as alternatives.

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

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

No annotations are provided, so the description carries the full burden. It discloses that the tool suggests directions based on inputs, which is sufficient for a recommendation tool. It does not mention limitations, but the behavior is transparent for the intended use.

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

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

Two concise sentences that front-load the purpose and input methods. No extraneous information.

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

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

The description lacks details about the output format or depth of suggestions. Given the complexity (5 parameters, two modes) and no output schema, more context on return value would improve completeness.

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

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

Schema coverage is only 20%, but parameter names are self-explanatory (interests, strengths, favoriteSubjects). The description explains the two modes (test_result and conversational) but does not detail individual parameters beyond that. This is adequate but not compensating fully for low coverage.

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

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

The description clearly states the tool's function: suggesting suitable majors/careers based on interests and strengths. It distinguishes between two input modes (test result code or conversational input), setting it apart from sibling tools like explore_job or get_major.

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

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

The description specifies input types (test code or conversational), giving clear context on when to use. It does not explicitly mention when not to use or alternatives, but sibling tool names provide implicit guidance.

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

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

No annotations provided, so description must cover behavior. It mentions save/read/update but omits delete action (present in enum). No disclosure of required fields, output format, or authentication needs. Privacy recommendation is good but insufficient.

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

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

Two sentences, no fluff. First sentence states purpose and key fields, second provides a privacy tip. Front-loaded and concise.

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

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

Given the tool's complexity (nested objects, enum action) and lack of output schema, the description is complete enough for basic understanding but misses details like what 'list' returns, delete behavior, and data structure semantics.

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 low (33%). The description adds privacy context for studentKey and lists portfolio fields, but does not explain action enum values or that data is optional. Adds some value beyond schema but not fully compensating.

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

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

Description clearly states the tool saves/reads/updates a student portfolio with specific fields (interests, score band, wishlist, memo). The verb and resource are specific, and it distinguishes from sibling tools like compare or search_major.

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. Does not mention when not to use it or provide context for choosing portfolio over other tools.

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

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

With no annotations, the description must disclose behavioral traits. It only states the tool explores departments and the data source. It omits whether the operation is read-only, required permissions, rate limits, or any side effects. As a search tool, the read-only nature is implied but not explicit.

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, well-formed sentence that conveys the core purpose and data source. Every element earns its place with no wasted words.

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

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

For a search tool with three optional parameters and no output schema, the description is incomplete. It doesn't explain parameter combinations, result format, or behavior when multiple filters are applied. The source is mentioned but the agent lacks information on what to expect in the response.

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

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

Schema coverage is 100% with descriptions for all three parameters. The tool description does not add meaning beyond the schema; it merely reiterates 'keyword·계열'. Therefore, the description meets the baseline but provides no additional semantic value.

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

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

The description clearly states the tool explores university departments by keyword and field. It uses a specific verb '탐색합니다' and resource '대학 학과', and the source is noted. The purpose is distinguished from sibling tools like get_major and search_university by focusing on exploration by keyword/field.

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 its siblings (e.g., get_major, search_university). The description does not mention constraints, prerequisites, or when not to use it.

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

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

With no annotations, the description must disclose behavioral traits but only describes the query action as a data retrieval. It does not state that it is read-only, whether side effects exist, if authentication is required, or how results are paginated. The source mention provides some trust but not behavioral clarity.

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 well-formed sentence that front-loads the main action and lists the key indicators. It includes a source attribution without unnecessary words. However, it could be slightly more structured (e.g., separating the list of indicators) for easier parsing.

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 5 optional parameters, no output schema, and no annotations, the description is incomplete. It does not mention that all parameters are optional, what the default search returns, or the format of results. Key details like pagination, result count, or data structure are missing, leaving the agent uncertain about how to interpret the output.

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

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

The description adds no parameter-level details beyond the input schema. Although schema coverage is 60%, the description does not explain how region, field, establishment, majorName, or year affect the search. For parameters without schema descriptions (establishment, majorName), the description offers no compensation, leaving ambiguity about their meaning or allowed values.

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

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

The description clearly states that the tool searches for universities with department offerings and returns key indicators (competition rate, tuition, etc.), using a specific verb '조회합니다' (inquire/retrieve). It distinguishes from siblings like search_major (which likely focuses on departments) by mentioning both universities and specific indicators, but it does not explicitly contrast with other 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 like search_major, explore_job, or get_major. There is no mention of prerequisites, conditions that trigger use, or cases where this tool is inappropriate. The agent must infer usage entirely from the name and sibling context.

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