ssuMCP

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

Annotations already indicate destructiveHint=true, so the description's mention of 'cancel' aligns. The description adds that it cancels an 'active' wait that hasn't started, but doesn't provide further behavioral details (e.g., irreversible effects). Given the annotation coverage, a score of 3 is appropriate.

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

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

The description is a single sentence that efficiently communicates the tool's purpose and a key requirement. No superfluous words or redundancy.

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

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

For a simple cancellation tool with one parameter and no output schema, the description provides the essential context: what it cancels and the required session. It could mention error conditions (e.g., if no active wait exists) but is largely sufficient.

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

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

The input schema provides 100% coverage for the single required parameter, including a description of mcp_session_id. The description only repeats the need for this parameter without adding new meaning. Baseline of 3 is correct.

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 ('cancel') and the specific resource ('active library seat waiting intent that hasn't started reservation'). It distinguishes this tool from siblings like wait_for_library_seat or get_library_wait_status by specifying it's for cancellation.

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

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

The description mentions the required mcp_session_id from LIBRARY login, implying the agent must have authenticated first. It does not explicitly list when to use or not use this tool versus alternatives, but the purpose is clear enough that an agent can infer the usage context.

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

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

The description adds operational context beyond annotations: it requires prior authentication and targets the u-SAINT system. This augments the readOnlyHint=true annotation without contradiction.

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 (one sentence) and front-loads the core purpose. It efficiently communicates the action and prerequisite.

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

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

For a simple tool with one parameter and no output schema, the description adequately covers what the tool does and the requirement for authentication. It could mention error cases but is largely sufficient.

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

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

Schema coverage is 100%. The description reiterates the need for mcp_session_id, adding no new semantic meaning beyond what the schema already provides.

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

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

The description clearly states the tool checks graduation eligibility and requirement fulfillment for authenticated students. It uses a specific verb ('check') and resource, but does not explicitly distinguish from the sibling 'evaluate_graduation_with_policy'.

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

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

The description specifies the prerequisite of an mcp_session_id from SAINT login, but provides no guidance on when to use this tool vs. alternatives like evaluate_graduation_with_policy.

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

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

Annotations already indicate readOnlyHint=true and destructiveHint=false. The description adds context about the return structure (decision/matchedRequirements/evidence) and the live vs seed corpus option via the 'live' parameter, which aids behavioral understanding.

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

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

Two sentences: first explains the tool's function and output, second provides usage guidance with an alternative tool. No wasted words, front-loaded with key information.

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

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

With 8 optional parameters and no output schema, the description covers the core functionality and output structure. It mentions live/seed modes but could elaborate on the official regulations source. Still, it is fairly complete for the complexity level.

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

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

Schema coverage is 100%, so parameters are already well-described. The description groups some parameters (GPA, earned credits, etc.) but does not add significant meaning beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states it checks scholarship policies by comparing queries and optional conditions against official regulations and returns decision/matchedRequirements/evidence. It distinguishes from the sibling tool get_my_scholarships, which handles individual scholarship history.

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

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

The description explicitly mentions using get_my_scholarships for individual history, providing when-not-to-use guidance. However, it could be more explicit about when to use this tool versus other siblings like check_graduation_requirements.

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

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

Annotations already declare readOnlyHint=true, so safety is clear. The description adds that the tool classifies and recommends, but does not describe how classification works or any dependencies. With annotations covering safety, a 3 is appropriate.

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?

A single, well-structured sentence that conveys the tool's purpose and output clearly without any 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?

Despite no output schema, the description sufficiently explains the output (classification and tool recommendation) and the single input. For a classification tool with clear intent, this is largely complete.

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

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

Schema coverage is 100% for the single parameter 'query', which has a description and example. The description adds no further parameter meaning beyond the schema. Baseline 3 applies.

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

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

The description clearly states the tool classifies academic questions into specific intents (graduation/scholarship/schedule/general regulations) and recommends a next ssuMCP tool. This distinguishes it from sibling tools that perform specific queries rather than classification.

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

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

The description implies usage for routing academic questions but does not explicitly state when to use this tool versus alternatives, nor when not to use it. No exclusions or context 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?

Annotations already indicate not read-only, not destructive. Description adds context: supersedes previous pending actions, different handling for multiple pending, async/sync behavior. No contradiction.

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 detailed but somewhat lengthy as a single paragraph. Front-loaded with main purpose, but could be more concise by separating behavioral 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?

Covers prerequisites, behavior for single vs multiple pending, superseding, async/sync differences. No output schema, but mentions guidance for multiple pending. Missing explicit return format, but overall 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 has 100% coverage, baseline 3. Description adds value: explains action_id can be omitted for single pending action, and comes from prepare response; mcp_session_id from start_auth.

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

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

The description clearly states it confirms and executes prepared pending actions. It distinguishes itself from sibling prepare tools, and explains behavior for different action types (reserve async, others sync).

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

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

Provides explicit when to use: after preparing an action. Explains when not to use (multiple pending) and mentions alternative to check async results (get_library_wait_status). Specifies needed mcp_session_id.

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

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

Annotations set readOnlyHint=false and destructiveHint=false. The description adds behavioral context: async ZIP build, 20-minute download link validity, and prerequisite. No contradictions.

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

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

Two sentences front-load purpose and include all key details without waste. Highly 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?

For a tool with one required parameter, no output schema, and clear annotations, the description fully explains the process, timing, and requirements. Complete enough for an 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 coverage is 100% with description for mcp_session_id. The tool description adds only the context that it's needed for LMS login, which is already in schema. Minimal extra meaning.

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

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

The description clearly states the tool approves a pending LMS material export, triggers async ZIP build, and returns a download link. It does not explicitly differentiate from sibling tools like 'prepare_lms_material_export' but the specificity is high.

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

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

The description implies usage after preparing an export and requires mcp_session_id, but it does not mention when not to use or provide explicit alternatives among siblings.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the tool's safety is clear. The description adds that it returns combined status and policy, but does not disclose additional behavioral traits beyond what annotations provide. No contradictions.

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

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

The description is a single, front-loaded sentence with no redundant information. Every word adds value.

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

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

Given the moderate complexity (returns status and policy basis) and no output schema, the description is somewhat thin. It lacks details on return format, pagination, or error cases beyond what the parameter schema implies. Adequate but not complete.

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

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

Schema coverage is 100%, so the parameters are fully described in the schema. The description does not add additional meaning or examples beyond what the schema provides. Baseline 3 is appropriate.

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

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

The description clearly states that the tool returns graduation requirement status with policy basis. It is specific and actionable, but does not explicitly differentiate from the sibling tool 'check_graduation_requirements'.

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

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

The description mentions that mcp_session_id is required (SAINT login) but provides no guidance on when to use this tool versus alternatives like check_graduation_requirements. No when-not-to-use or explicit 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?

Discloses that the tool returns a preview (file list, counts, sizes, exclusions) and that confirmation via confirm_lms_material_export is needed for the ZIP download. Mentions auto-exclusion of video/audio files and requirement of mcp_session_id. Adds significant context beyond annotations (readOnlyHint=false, destructiveHint=false).

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 detailed but slightly verbose. It covers usage, flow, output, and exclusions in multiple sentences. While informative, it could be more concise.

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

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

For a tool without an output schema, the description adequately covers the return content (preview with per-course details), next steps, and exclusions. It provides a complete picture of the tool's behavior and expected flow.

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%. The description adds that term_id defaults to the current active semester, which is useful but not extensive. No additional semantics for mcp_session_id beyond the schema.

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

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

The description clearly states the tool is for bulk downloading all LMS materials when the user explicitly requests 'all materials' or 'all subjects'. It distinguishes from siblings by specifying the condition and providing an alternative flow for single-subject requests.

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

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

Explicitly states when to use (only on explicit bulk download request) and when not to use (for single-subject requests, instead use get_my_lms_courses → prepare_lms_material_export). Provides a clear alternative.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds filtering behavior but no additional behavioral traits like response format or pagination, which would be expected beyond schema.

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

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

The description is only two sentences, front-loaded with the main function, and every word adds value. No wasted 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 simplicity (4 optional params, no output schema, no nested objects) and the presence of annotations and schema, the description is mostly complete. It could mention default behavior for year, but the schema covers that.

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

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

Schema description coverage is 100%, so the baseline is 3. The description only restates the filter parameters without adding new meaning or usage details beyond the schema.

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

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

The description clearly states the tool returns academic calendar events with filtering by year, month, and keyword, and provides specific examples like course registration and exams, distinguishing it from siblings such as get_academic_calendar.

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

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

The description gives context by mentioning use cases (e.g., searching for registration, semester start/end), but does not explicitly state when not to use it or mention alternatives among the many sibling tools.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds behavioral details: date formats (ISO), null endDate for single-day events, and default year behavior. This provides context beyond 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 concise: one sentence for purpose, one for return format details, one for default behavior. It is front-loaded and every sentence adds value.

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

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

Despite no output schema, the description explains the return structure and field meanings. For a simple read-only query with one optional parameter, the description covers essential context completely.

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 one parameter described (year). The description reiterates the year default behavior, adding little new meaning. Baseline 3 applies as the schema already provides sufficient 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 clearly states the tool retrieves academic calendar from Soongsil University, specifies the return format (list of objects with date, endDate, event, category), and explains edge cases (endDate null for single-day events). It distinguishes itself from sibling tools like find_academic_calendar_events by being the direct calendar query.

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

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

The description implies usage for viewing academic schedules but does not explicitly state when to use this tool over siblings like find_academic_calendar_events. No when-not-to-use or alternative guidance is provided.

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

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

Annotations already indicate readOnlyHint=true and destructiveHint=false. Description adds that it returns evidence with source URL, revision history, and live/fallback status, which provides useful behavioral context beyond annotations.

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

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

Two concise sentences. First states purpose, second clarifies output format. No unnecessary information.

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

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

Given the tool's complexity (4 parameters, no output schema), the description explains return format partially (source URL, revision history, status) but lacks detail on parameter usage (e.g., when to set live or category) and does not differentiate from 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%, so parameters are already documented. Description does not add significant extra meaning beyond mentioning live/fallback status, but it is not misleading.

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

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

Description clearly states it returns source-based evidence summaries for academic questions, distinguishing from direct answers. However, it does not explicitly differentiate from sibling tools like check_graduation_requirements or check_scholarship_policy, which may also provide evidence but are more specific.

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

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

No guidance on when to use this tool versus alternatives. Does not specify when to prefer this over siblings, nor conditions for using parameters like live or category.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds the key behavioral trait of filtering for active notices, which is useful context beyond 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 consists of two concise sentences that are front-loaded with the core purpose. Every sentence adds value with no extraneous content.

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

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

For a simple read tool with one optional parameter and no output schema, the description explains the return filter and use case adequately. It could mention ordering or pagination, but is mostly complete.

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

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

The input schema has 100% coverage with a description for the optional 'category' parameter. The tool description does not add any additional meaning beyond what the schema already provides, so baseline score of 3 is appropriate.

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

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

The description clearly states the tool returns only active (pre-deadline) notices and explains its utility for checking imminent or currently applicable notices. This verb+resource combination distinguishes it from sibling tools like get_recent_notices.

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

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

The description provides clear context for when to use the tool (checking active notices). However, it does not explicitly state when not to use it or mention alternatives, which would strengthen 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?

Beyond annotations (readOnlyHint, destructiveHint), description explains that sessions persist after server restart and that missing/invalid ID marks providers as unlinked. Adds 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?

Description is a single clear paragraph with enumerated statuses and practical advice. No redundancy, but a bit dense for non-Korean readers? Still 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?

All relevant info is present: status meanings, persistence, pre-auth advice. No output schema needed; the return format is well-explained in the description.

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

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

Schema already covers the single optional parameter fully. Description adds context on how the parameter affects the status outcome but no new syntax or format details. Baseline 3.

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

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

Description clearly states it returns MCP auth session status, enumerates possible status values with meanings, and distinguishes from auth-creation tools by advising to call this before to avoid retries.

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

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

Explicitly recommends calling before other auth tools to reduce AUTH_REQUIRED retries, and explains how to handle each status (e.g., use start_auth for INVALID_SESSION). Could be more explicit about when not to use.

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

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

Annotations already indicate readOnlyHint=true and destructiveHint=false, so the description does not need to reiterate safety. It adds no additional behavioral context beyond the basic function, which is acceptable for a read-only tool.

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

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

Single sentence with essential information, no wasted words. The department example list is concise and helpful.

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 list tool with complete schema coverage and clear annotations, the description is adequate. It lacks details about return format but no output schema exists, so the burden is low.

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

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

Schema coverage is 100%, so the description's mention of department examples does not add significant meaning beyond the schema. The page parameter is not elaborated, but the schema already describes it.

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 returns notices for a specific department, using the Korean verb '반환합니다'. It distinguishes from siblings like 'get_recent_notices' and 'search_notices' by specifying department filtering.

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 provides examples of department names but does not explicitly state when to use this tool versus alternatives. Usage is implied through the department filter, but no when-not or alternative guidance is given.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description adds value by specifying the return includes 7 days of meals and holiday info. No contradictions, and the description adequately discloses the tool's behavior beyond 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, well-structured sentence in Korean that conveys all necessary information without 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 no parameters and no output schema, the description fully explains what the tool does and what it returns. It is complete for a simple read-only query 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?

No parameters exist, so schema coverage is 100%. The description adds context about what is returned (7 days, meals, holiday info), which is useful beyond the empty schema.

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

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

The description clearly states it queries the weekly menu of the residence hall cafeteria, returning 7 days of breakfast/lunch/dinner and closed days. The verb '조회합니다' is specific, and it distinguishes from sibling tools like get_meal_by_date and get_today_meal.

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

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

The description does not explicitly state when to use this tool vs alternatives. While the purpose implies it for weekly overview, no direct guidance is provided for choosing between this and similar tools like get_meal_by_date or get_today_meal.

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

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

Annotations already mark readOnlyHint=true and destructiveHint=false. The description adds value by explaining that away-status seats are included and that the tool performs a real-time query. This expands on the basic safety annotation with operational 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 (6 sentences) and well-structured: purpose, return values, special status, linkage to other tools, alternative tool suggestion, and login requirement. Every sentence serves a clear role 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?

The tool has a simple interface (one required param) and no output schema. The description fully compensates by listing return elements (available seats count, externalSeatId list, seat numbers) and noting away status. Sibling differentiation and login requirement complete the 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 coverage is 100% with one parameter (mcp_session_id) already described. The description reinforces its purpose and source (LIBRARY login), adding no ambiguity. Baseline 3 is elevated to 4 due to confirmation and clarity.

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

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

The description clearly states the tool's purpose: real-time inquiry of reservable seats in all 7 reading rooms. It uses specific verbs ('조회합니다', '반환합니다') and explicitly differentiates from the sibling tool 'get_room_available_seats' by noting it for overall status vs. room-specific detail.

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

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

The description explicitly guides when to use this tool (overall status) and when to use 'get_room_available_seats' (specific room detail). It also states the prerequisite of an mcp_session_id from LIBRARY login and notes that externalSeatId is used with 'prepare_reserve_library_seat', providing clear usage context.

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

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

Description adds beyond annotations: states no real-time data, no authentication, built from screenshots. Annotations already indicate read-only and non-destructive; description complements with specifics.

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?

Concise with front-loaded primary purpose. Minor redundancy (인증 불필요 mentioned twice) but overall efficient.

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

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

Complete for a simple, read-only tool: covers purpose, behavior, usage hint, and parameter context. No output schema 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 coverage is 100% with descriptions for each parameter. Description briefly mentions include_layout but adds little beyond schema. Adequate but no extra depth.

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 returns a static catalog of library seat layouts, distinguishes from real-time seat tools, and specifies no authentication needed. Verb 'returns' with specific resource.

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

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

Describes when to use (static layout, not real-time) and mentions the include_layout parameter for text-based layout. Does not explicitly name alternative sibling tools for real-time data, but context is clear.

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

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

The description adds behavioral context beyond annotations: it confirms the tool is read-only, explains auth requirements, and specifies that unauthenticated requests return AUTH_REQUIRED with a loginUrl. This aligns with readOnlyHint=true and destructiveHint=false, adding value.

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 and front-loaded with the main purpose. It covers necessary details in a few sentences without redundancy. Minor improvement could be made by structuring bullet points, but it is already efficient.

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

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

Given the tool's simplicity (3 parameters, no output schema), the description is complete: it explains purpose, auth requirement, compact option, and differentiation from reservation tools. No critical gaps remain for a read-only query tool.

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

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

Schema description coverage is 100%, so the baseline is 3. The description clarifies the compact parameter's effect and mentions floor values, but does not add significant new meaning beyond the schema's descriptions. Thus, a 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 retrieves current seat status by floor, including totals and area distribution. It mentions compact support and auth requirement. However, it does not explicitly differentiate from sibling tools like get_library_available_seats or recommend_library_seats, though the context implies this is a floor-level overview.

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

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

The description provides context for when to use the tool: it is read-only and seat reservation is a separate tool. It also explains the need for mcp_session_id and the behavior when unauthenticated. It does not explicitly list alternatives or when not to use, but the context is clear enough.

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

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

The description aligns with annotations (readOnlyHint=true, destructiveHint=false) by stating it queries status. It adds the behavioral detail of omitting intent_id returning the most recent intent. Since annotations already indicate a safe read operation, the description provides minimal additional context beyond that.

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—only two sentences in Korean—and front-loads the purpose. Every sentence is necessary, with no redundancy or wasted words.

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

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

The description covers all parameters and usage scenarios. However, it does not describe the return format or possible status values, which could be useful for an agent without an output schema. Still, for a read-only query, it is mostly complete.

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

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

Schema coverage is 100%, but the description adds meaning by explaining the two use cases for intent_id (single vs. multiple intents) and that mcp_session_id is obtained from LIBRARY login. This adds value beyond the schema descriptions.

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

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

The description clearly states the tool queries the status of library seat wait/reservation intents. It distinguishes between omitting intent_id (most recent) and specifying it (specific intent), which differentiates it from sibling tools like wait_for_library_seat and cancel_library_wait.

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

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

The description provides clear guidance on when to omit or specify intent_id, mentioning typical single-intent cases and multi-intent scenarios like confirm_action. It also notes the dependency on mcp_session_id from LIBRARY login, but does not explicitly exclude alternative tools.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds useful behavioral context: authentication is required (start_auth), and term_id is optional with auto-selection of the current term. No contradictions with annotations.

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

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

Three sentences, each earning its place: purpose, parameter behavior, authentication instruction. No filler or redundancy. Front-loads the main 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?

The description lists the data categories summarized (assignments, quizzes, calendar, notices) which gives a clear idea of the output content. No output schema exists, but the description is sufficient for most agents to understand what the tool returns. Could optionally mention output format.

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

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

With 100% schema coverage, baseline is 3. The description adds meaning beyond schema by clarifying that omitting term_id auto-selects the current term and explaining the authentication flow for mcp_session_id. This is valuable for correct invocation.

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 summarizes overdue assignments, quizzes, academic calendar events, and ongoing notices for authenticated users. The verb 'summarizes' and the resource 'LMS dashboard' are specific, and the tool is distinct from siblings like get_my_assignments or get_academic_calendar which fetch individual data.

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 explains how to use the tool: authentication via start_auth and MCP session ID, and optional term_id with auto-selection. It does not explicitly state when to use this aggregated dashboard versus individual tools, but the implied context (one-stop summary) provides some 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?

Annotations already declare readOnly and non-destructive. Description adds behavioral context: returning all corner menus and holiday info when restaurant is empty. No contradictions.

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

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

Two sentences, front-loaded with main purpose, no unnecessary words. Each sentence adds distinct value.

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

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

For a simple query tool with well-described parameters, the description fully covers usage scenarios. No output schema needed for menu listing; description suffices.

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 100% of parameters but description adds meaning: exact ISO date format for 'date' and enumerates possible Korean values for 'restaurant'. Also explains empty behavior, which schema doesn't cover.

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 action (조회) and resource (숭실대학교 학생식당 메뉴) with specific date format. It distinguishes from sibling 'get_today_meal' by supporting arbitrary dates, and explains behavior based on restaurant parameter.

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 explicitly explains two usage modes: leaving restaurant empty for all restaurants vs. specifying one. It provides clear context on when to use each, but does not mention when not to use this tool or alternatives beyond siblings.

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

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

Annotations already indicate readOnlyHint=true and destructiveHint=false. The description adds context about the weekly nature and weekOffset behavior but does not disclose additional traits like data freshness, caching, or response format. The added value is moderate.

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 and front-loaded, with two sentences covering purpose, parameter behavior, and sibling differentiation. No unnecessary words.

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

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

For a simple read-only tool with one optional parameter and no output schema, the description is complete. It clearly states the tool's function, parameter semantics, and distinguishes it from the dormitory menu 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?

The input schema fully describes the weekOffset parameter (100% coverage). The description adds significant value by explaining the offset's meaning (0=this week, 1=next week) and the default behavior (Monday to Sunday), which goes beyond the schema's brief 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 retrieves weekly menus for the Soongsil University student cafeteria, specifying the date range (7 days). It distinguishes itself from the sibling tool get_dorm_weekly_meal, which is explicitly mentioned for dormitory menus.

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 explains when to use the tool (weekly menu) and explicitly directs users to get_dorm_weekly_meal for dormitory menus. It also explains the weekOffset parameter's effect (0=this week, 1=next week). However, it does not mention when to avoid it or compare with other meal-related siblings like get_today_meal.

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?

Discloses non-auth behavior (returns AUTH_REQUIRED with loginUrl) and instructions for re-calling after login. Beyond annotations (readOnlyHint, destructiveHint), it adds critical context about session requirements and auth flow.

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 paragraph with front-loaded purpose, no fluff. All sentences are necessary and informative. Length is appropriate for the complexity.

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?

No output schema, but description implies return of unsubmitted assignments/quizzes and mentions auth error format. Could be more explicit about the structure (e.g., list of assignments), but overall sufficient for a read-only tool with simple 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 covers 100% of parameters with descriptions. Description adds value by clarifying compact behavior (name/deadline only vs details) and that term_id defaults to LMS default. This extra context justifies above baseline 3.

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

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

The description clearly states it retrieves unsubmitted LMS assignments and quizzes for authenticated students, with a specific verb and resource. It distinguishes from sibling tools focused on course lists or dashboards.

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

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

Provides explicit guidance: requires mcp_session_id, compact parameter support, default term behavior, and references sibling tool get_my_lms_terms for other terms. Also explains authentication failure handling with loginUrl.

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

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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description adds behavioral context: authentication requirement (mcp_session_id from SAINT login), default behavior for omitted parameters, and reference to AUTH_REQUIRED error with loginUrl (implied by schema description of mcp_session_id). No contradictions.

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

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

Two sentences with clear structure: purpose in first, parameter details in second. No unnecessary 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 covers purpose, parameters, and auth requirement. However, it does not describe the output format (e.g., list of attendance records) despite no output schema. Acceptable for a simple retrieval tool but could be more complete.

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

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

Schema coverage is 100%, so baseline is 3. The description adds that year and semester are optional and if omitted, the current semester is used, which provides meaning beyond the schema's individual parameter descriptions.

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

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

The description uses a specific verb ('조회', retrieve) and identifies the resource ('u-SAINT 채플 출석 정보', chapel attendance info) clearly. It distinguishes itself from sibling tools (e.g., get_my_grades, get_my_schedule) by specifying chapel attendance.

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 states that year and semester are optional and default to the current semester, and explicitly mentions the need for mcp_session_id from SAINT login. It does not explicitly exclude alternative tools, but the purpose is distinct enough to guide 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?

Annotations indicate readOnlyHint=true and destructiveHint=false. The description adds that the tool returns AUTH_REQUIRED if unauthenticated, explains the response includes loginUrl, and specifies the need for re-call after authentication. This provides behavioral context beyond 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, well-structured sentence that front-loads the purpose and then provides usage guidance. Every clause earns its place 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?

For a simple read-only tool with one parameter, the description covers authentication requirements, error handling, and the general nature of the response (grades and GPA history). While it does not detail the full response format, the lack of an output schema makes this acceptable.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the dynamic behavior of the mcp_session_id parameter (must be from start_auth, consequences of missing/invalid), which is not in the schema.

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

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

The description clearly identifies the tool as retrieving cumulative grades with semester GPA history for an authenticated student, using a specific verb and resource. It is distinct from sibling tools like get_my_assignments or check_graduation_requirements.

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

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

The description explicitly states the prerequisite (mcp_session_id required) and provides instructions for handling authentication failure (show loginUrl and guide user). It implies when to use but does not contrast with 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, confirming safe read-only operation. The description adds value by detailing the authorization requirement, the specific AUTH_REQUIRED response on failure, and the recovery flow, which goes beyond what annotations provide.

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. The first states the core purpose, the second explains the essential usage context and error handling. No extraneous information; front-loaded and efficient.

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

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

Given the tool's simplicity (one required param, read-only, no output schema), the description covers purpose, authentication requirement, and error handling. It mentions the output will include due dates, providing some expectation. Lacking only a full list of returned fields, but acceptable for this scope.

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 for the single parameter mcp_session_id is 100%, with a description already covering its source and error behavior. The tool description reiterates this but does not add new parameter-specific semantics beyond what the schema already conveys. 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?

Description clearly states the tool retrieves current library loans with due dates for authenticated users. The verb '조회' (retrieve) and resource '도서관 대출 현황' (library loan status) are specific. Among sibling tools, it is distinct from other library services like seat or catalog queries.

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

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

Explicitly notes that mcp_session_id from LIBRARY login is required and describes the authentication failure behavior (AUTH_REQUIRED with loginUrl), including instructions to guide the user to login and retry. While it doesn't specify when not to use or list alternatives, the guidance is clear and actionable.

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

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

Annotations already indicate read-only and non-destructive. Description adds context about no-seat case and auth requirement, enhancing 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?

Three concise sentences, each earning its place: main action, edge case, and sibling references. 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?

For a simple read-only tool without output schema, description adequately covers functionality and outcomes (seat info or none). Lacks explicit return structure but sufficient for 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%; description only reiterates the parameter's purpose, adding no extra meaning beyond schema.

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

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

Description clearly states the tool retrieves current reserved library seat info, distinguishes from siblings by naming cancel and swap 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?

Explicitly tells when to use (check reservation), provides alternatives for cancel and swap, and notes authentication requirement.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds context beyond: it returns aggregated data, automatically selects active term if term_id omitted, and requires mcp_session_id from LMS login. It also describes the output structure. However, it does not mention rate limits or performance characteristics.

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 paragraph of four sentences, front-loading the main purpose and then adding critical usage steps. It is concise and earns its place, though it could benefit from slightly more structured formatting (e.g., bullet points).

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

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

Without an output schema, the description fully explains what is returned (file count, total size, extension groups, content_id per course) and how to present it to the user. It also clarifies the relationship to sibling tools (prepare_lms_material_export) and the automatic term selection 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 coverage is 100% and the schema already describes both parameters (term_id: default to active term; mcp_session_id: from start_auth). The description reiterates these points but adds no substantial new meaning 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 clearly states it retrieves the authenticated user's LMS courses along with downloadable materials (files). It specifies the returned data per course (file count, total size, extension groups, content_id) and distinguishes from sibling tools by noting it replaces the need for get_my_lms_materials.

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

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

Explicitly says to call this right after login, that it is the only tool needed for initial overview, and that if a user selects a course, use content_id to call prepare_lms_material_export directly. It also tells the agent not to call get_my_lms_materials again.

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

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

Annotations indicate readOnlyHint=true and destructiveHint=false. The description adds that video/audio files are excluded due to security/size limits and that results are grouped by file extension with counts and details. This adds valuable behavioral context beyond the 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 concise but includes all necessary details (purpose, exclusions, defaults, prerequisites). It is front-loaded with the main purpose and then provides additional context. Could be slightly shorter, but efficient overall.

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), the description covers the purpose, return format (grouped by extension with counts), exclusions, default behavior for term_id, and prerequisite (mcp_session_id). This is sufficient for an agent to use the tool correctly.

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

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

Schema coverage is 100%, and the description adds meaning: term_id is optional and defaults to active term, course_ids are obtained from get_my_lms_courses, and mcp_session_id is for LMS login. This enriches the parameter understanding beyond the schema's basic descriptions.

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

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

The description specifies the action (조회, 'retrieve'), the resource (주차별 학습 자료, 'weekly learning materials excluding video'), and the grouping feature (파일 확장자별, 'by file extension'). It clearly distinguishes from sibling tools like export_all_lms_materials (export) and get_my_lms_courses (courses 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 mentions that term_id defaults to the current active term if not provided, and states the need for mcp_session_id (LMS login). It implicitly differentiates from export tools, but does not explicitly state when to use this tool versus alternatives 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?

Annotations already indicate readOnlyHint=true and destructiveHint=false. The description adds behavioral context about the defaultTerm field, explaining that only one semester has defaultTerm=true and it is used when term_id is omitted. This goes beyond the 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 concise with four sentences, each adding essential information: return fields, defaultTerm explanation, usage guidance, and authentication requirement. No unnecessary repetition or filler.

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 list tool with one parameter, the description covers all necessary aspects: return fields, meanings, usage in other tools, and authentication. Since there is no output schema, the description fully explains the response structure.

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

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

The input schema has 100% coverage with a description for mcp_session_id. The tool description mentions the requirement but adds no new semantic detail beyond what the schema already provides. 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 returns the user's LMS registered semester list with specific fields (id, name, dates, defaultTerm). It distinguishes from siblings by explaining how to use the returned id in other tools like get_my_lecture_list and get_my_assignments.

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

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

The description provides clear context for when to use this tool (to obtain semester list) and how to use the output with other tools. It does not explicitly state when not to use it, but no alternative tool exists for this purpose, so the guidance is sufficient.

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

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

Beyond annotations (readOnlyHint=true), the description discloses key behaviors: authentication dependency, return of loginUrl on failure, grouping by subject, and default semester behavior. No contradictions with annotations.

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

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

The description is compact (4 sentences) and front-loaded: the main action is stated first. Every sentence provides necessary information without redundancy or 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?

The description covers authentication and parameter usage well, but lacks explicit mention of the output format beyond 'grouped by subject.' Since there is no output schema, describing the response structure would improve completeness. However, the existing detail is sufficient for an agent to invoke the tool correctly.

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

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

Schema description coverage is 100%, and the description adds substantial value by explaining the interaction between year and term, providing term value mappings (1=spring, etc.), and detailing the mcp_session_id's role in authentication. This clarifies usage beyond 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 starts with '인증된 학생의 u-SAINT 시간표를 과목별로 묶어 조회합니다' which clearly states the purpose: retrieving the schedule for an authenticated student, grouped by subject. This differentiates it from sibling tools like get_my_grades or get_my_assignments.

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

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

The description provides explicit guidance: omitting year/term returns current semester, while specifying both retrieves a specific term. It also explains the authentication flow, including how to handle the AUTH_REQUIRED response. This covers when and how to use the tool effectively.

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?

Adds critical context beyond annotations: requires SAINT login via mcp_session_id, describes error behavior (AUTH_REQUIRED with loginUrl). No contradiction.

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

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

Two concise sentences, front-loaded with purpose, 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?

Adequate for a read-only tool with few parameters, though no output schema and output structure not described. Minor gap.

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

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

Adds value beyond schema: clarifies year is optional, explains mcp_session_id role and error handling. Schema already has 100% coverage.

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

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

Description clearly states verb (조회/retrieve) and resource (u-SAINT 장학금 수혜 내역). Distinguishes from sibling tools like check_scholarship_policy which focus on policy.

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

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

Implies usage for retrieving scholarship history of authenticated users with optional year filter. Lacks explicit guidance on when not to use or alternatives.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description confirms the read-only nature by stating it returns text, but adds no additional behavioral context beyond what the annotations provide.

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, effective sentence in Korean. It front-loads the purpose and includes essential usage instruction without any filler. Every word earns its place.

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

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

For a simple tool with one parameter and no output schema, the description is complete. It explains what the tool returns (full text), how to obtain the input (from sibling tools), and implicitly conveys that the output is plain text. No additional information is necessary.

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

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

The input schema covers 100% of parameters, with a clear description for the 'url' field. The description repeats the schema's guidance ('get_recent_notices/search_notices 결과의 link 값') without adding new meaning or format details. 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 returns the full text of a notice given its URL. It specifies the resource ('본문 전체 텍스트') and action ('반환합니다'), and implicitly distinguishes from sibling tools that list or search notices by requiring a specific URL as input.

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

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

The description explicitly instructs the agent to pass the 'link' value from get_recent_notices or search_notices results as the input. This provides clear context on when and how to use the tool, effectively guiding the agent away from incorrect usage.

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

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

Annotations already indicate read-only (readOnlyHint=true) and non-destructive (destructiveHint=false). The description adds that compact=true returns only title/URL, which is hinted in the schema. However, it does not discuss pagination behavior or response structure beyond the schema.

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

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

The description is extremely concise with three short sentences. The first sentence directly states the purpose, followed by filtering details and cross-reference to another tool. Every sentence earns its place.

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

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

The description covers the main functionality and references category lookup, but lacks details on the return format (e.g., whether it includes pagination metadata) and pagination behavior. Since there is no output schema, more detail would be beneficial for completeness.

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

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

The input schema covers all three parameters (page, compact, category) with descriptions, achieving 100% coverage. The description does not add new semantic meaning beyond what is in 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 it retrieves the latest list of Soongsil University notices with optional category filtering, which differentiates it from sibling tools like 'search_notices' that likely perform broader search. However, it does not explicitly distinguish from 'get_active_notices' or 'get_department_notices'.

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

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

The description mentions that categories can be obtained via 'list_notice_categories', which is helpful, but it provides no guidance on when to use this tool versus alternatives like 'search_notices' or 'get_active_notices'. There is no scenario-based advice.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description confirms it is a real-time query but adds no additional behavioral traits beyond the output fields. It provides context but does not significantly extend transparency beyond the 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 concise (three sentences) and front-loads essential information: real-time query, output fields, room IDs, and linkage to another tool. Every sentence serves a purpose 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 absence of an output schema, the description adequately explains the output fields (seat status, label, type, remaining time). It also provides necessary context about authentication and integration with the reservation tool, making it complete for a read-only query 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?

The schema already covers 100% of parameters, describing roomId and mcp_session_id. The description repeats the valid room ID values and the need for mcp_session_id, adding marginal semantic value beyond the schema.

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

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

The description clearly specifies that the tool retrieves real-time seat status for a specific reading room, lists valid room IDs, and details the output fields (status, label, type, remaining time). It also mentions how the output is used (externalSeatId for prepare_reserve_library_seat), distinguishing it from other library seat tools like get_library_available_seats.

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 explains that the tool requires an mcp_session_id from LIBRARY login and lists all valid room IDs. It also indicates the linkage to prepare_reserve_library_seat. However, it does not explicitly differentiate from sibling tools like get_library_available_seats, so the guidance is very good but not maximally precise.

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

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

Annotations declare readOnlyHint=true, and the description adds context: it describes that empty argument returns all corners' menus and closure info, and specifying a restaurant restricts results. This goes beyond annotations.

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

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

Two sentences, front-loaded with main purpose, no extraneous words. Efficient and clear.

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

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

Given the tool's simplicity (one optional parameter, no output schema), the description fully covers behavior for both parameter states and provides all needed 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 coverage is 100% for the single parameter, and the description adds meaning by explaining the effect of empty vs specified values, and lists possible restaurant names. It enhances the schema 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 retrieves today's meal from Soongsil University student cafeteria, explains the behavior for empty vs specified restaurant argument, and distinguishes it from sibling tools like get_meal_by_date by specifying 'today'.

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 explains when to leave restaurant empty (returns all campus restaurants) vs specifying a restaurant (filters). It implicitly differentiates from siblings but does not explicitly state when not to use.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description adds minimal behavioral context beyond confirming read-only behavior. It mentions checking 'live 지원 여부' which matches the schema parameter, but does not disclose any additional traits like data freshness, authorization needs, or response volume.

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 short paragraph in Korean, efficiently stating the purpose and output fields. It is front-loaded and contains no redundant information. However, it could be restructured with bullet points for better scanability.

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 low complexity (zero required params, simple list operation) and the presence of annotations, the description adequately covers the output fields (URL, contentUrl, revision/effectiveDate, live support, verification date). It also hints that results can be filtered by 'live' and 'category' parameters. Though lacking pagination details, it is sufficient for a list 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 both parameters clearly documented. The description repeats some aspects (e.g., 'live 지원 여부') but does not add meaning beyond the schema descriptions. Baseline score of 3 is appropriate as the description does not significantly 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 returns a list of official sources queried by the academic RAG, specifying the attributes (URL, contentUrl, revision/effectiveDate, live support, verification date). The name 'list_academic_policy_sources' is specific and distinguishes from sibling tools like 'search_academic_policy_sources' which suggests searching within those sources.

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 explains what the tool does but does not provide explicit guidance on when to use it versus alternatives such as 'search_academic_policy_sources' or other policy-related tools. The context signals include many siblings, but the description lacks usage cues, leaving the agent to infer from 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description adds only the context of returning a list and its relationship to other tools. No additional behavioral details like output format are provided.

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

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

Two sentences with no wasted words. The purpose and usage context are front-loaded and clear.

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

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

Given the zero parameters and no output schema, the description is complete enough for a simple category list tool, but it could mention the output type (e.g., names/IDs) without being necessary.

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

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

There are no parameters, and schema coverage is 100%. The description adds no parameter details, but with no parameters this is acceptable; baseline 4 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 returns a list of notice categories and explicitly links its utility to the category parameter of sibling tools get_recent_notices and search_notices, distinguishing it from 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 clear context for when to use the tool (to check category values for other tools) but does not explicitly state when not to use it or list alternatives.

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

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

Annotations already indicate destructiveHint=true. The description adds that it removes 'all providers' and requires a session ID, providing specificity beyond annotations. No contradiction.

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, concise sentence that efficiently conveys the core functionality and required parameter 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 simple one-parameter tool with no output schema, the description is adequate. It could mention return value or side effects, but annotations cover destructiveness.

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

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

Schema coverage is 100% and the description simply restates the parameter purpose without adding new meaning. 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 removes all providers connected to an MCP auth session, which is a specific verb+resource. It distinguishes from sibling 'logout_provider' which likely affects a single provider.

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

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

The description clearly states what the tool does and its required parameter, but does not explicitly compare with alternatives like 'logout_provider'. However, context from sibling names suggests when to use this holistic logout.

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

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

Annotations indicate destructiveHint=true, and the description confirms the disconnect action. However, no additional details on side effects (e.g., session validity after logout) are provided, which would enhance 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 concise sentence that covers the action and required parameters. No redundant information, though structure could be slightly improved by separating action from constraints.

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 logout action with two well-documented parameters, the description is adequate but lacks return value information and context about when to choose this over 'logout_all'. Missing behavioral 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?

Schema coverage is 100%, and both parameters have clear descriptions. The description adds no new meaning beyond what the schema already provides, meriting a baseline score.

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

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

The description clearly states the tool disconnects a specific provider from the MCP session, listing the allowed providers. It implies per-provider logout but does not explicitly distinguish from sibling 'logout_all'.

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

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

No guidance on when to use this tool versus alternatives like 'logout_all'. No prerequisites or context provided beyond parameter requirements.

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

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

The description adds context beyond annotations: it is a preparation step that does not execute cancellation alone, it auto-queries reservation info, and requires a LIBRARY session. Annotations indicate non-destructive and read-write, which aligns with the preparatory nature.

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

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

The description is three sentences long, front-loaded with purpose, and each sentence provides necessary information without redundancy. It is efficient but could be slightly more structured.

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

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

Given the tool's simplicity (one parameter, no output schema, destructive hints from annotations), the description covers the essential context: purpose, need for confirm_action, and prerequisite. It is complete enough for an agent to use correctly.

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

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

The schema already fully describes the single parameter (mcp_session_id) with 100% coverage. The description repeats the requirement for a LIBRARY login but adds no new semantic detail beyond the schema.

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

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

The description clearly states the tool cancels a reserved library seat at Soongsil University Central Library. It distinguishes itself from the final action by noting that confirm_action is required, and from sibling 'cancel_library_wait' by focusing on current reservation cancellation.

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 explains when to use (to cancel a reserved seat) and that confirm_action must follow. It also notes that no reservation number is needed due to auto-query. It does not explicitly state when not to use or compare with alternatives, but the context is clear.

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

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

Annotations only indicate readOnlyHint=false and destructiveHint=false. The description adds significant behavioral context: it validates, prepares queue registration, checks limits, excludes unsupported files, and requires mcp_session_id for LMS login. No contradiction with annotations.

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

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

The description is five sentences in Korean, front-loaded with purpose, then usage flow and constraints. Every sentence adds necessary information without repetition or 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?

The description lacks details about the return value or what the agent should expect after calling this tool. It mentions 'validates and prepares queue registration' but does not clarify whether it returns a success status, an export identifier, or requires a follow-up action. Given no output schema, this is a gap.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining that content_ids come from get_my_lms_courses response and mcp_session_id is for LMS login. This goes beyond the schema's basic type descriptions.

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

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

The description clearly states it validates and prepares export of LMS weekly learning materials (PDF, PPT) for a specific subject. It uses specific verb 'prepare' and resource 'LMS material export', distinguishing it from siblings like confirm_lms_material_export and export_all_lms_materials.

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

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

The description provides clear prerequisite: call get_my_lms_courses first to get content_ids, and explicitly says not to call get_my_lms_materials again. It also mentions that unsupported or over-limit files are excluded. It does not explicitly state when not to use, but gives sufficient usage context.

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

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

The description adds value beyond annotations: it reveals that authentication via LIBRARY is required (mcp_session_id), that the tool only prepares and does not execute, and provides concrete instructions for parameter sourcing. Annotations already indicate non-read-only and non-destructive, but the description elaborates on behavioral context without contradiction.

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 (four sentences) and front-loaded with the main purpose. Every sentence serves a clear function: stating purpose, clarifying the two-step process, specifying required session, and detailing seat_id sourcing. 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 tool's moderate complexity (2 required params, no output schema), the description covers prerequisites, input sources, and workflow positioning. A minor gap is the lack of mention about what the preparation returns (e.g., a token for confirm_action), but this is implicitly understood from the tool's role in the system.

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

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

With 100% schema coverage, the description still adds significant meaning: it maps mcp_session_id to the LIBRARY authentication context and seat_id to specific sources (externalSeatId from recommend_library_seats or URL from oasis.ssu.ac.kr). This provides actionable semantics beyond the schema's simple type descriptions.

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

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

The description clearly states the tool prepares a library seat reservation at Soongsil University Central Library, explicitly noting that it does not execute the reservation (confirm_action needed). It distinguishes from sibling tools like confirm_action and recommend_library_seats by explaining the two-step process and specifying how to obtain the seat_id.

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

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

The description provides explicit guidance on when to use this tool: before calling confirm_action. It explains that reservation is not complete with this tool alone, specifies prerequisites (LIBRARY login via mcp_session_id), and gives two methods to obtain seat_id (from recommend_library_seats or directly from the website). This helps the agent choose the correct tool and sequence.

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

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

Annotations indicate readOnlyHint=false and destructiveHint=false. The description explains that the tool is a preparatory step that does not finalize changes until confirm_action is called, which adds context beyond annotations. It also mentions auto-retrieval of current reservation info. Slight lack of detail on error states but overall good.

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 yet comprehensive, covering purpose, workflow, alternatives, and prerequisites in three sentences. No superfluous information; every sentence adds value. Front-loaded with the core action.

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

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

For a complex tool with a two-step process and conditional usage, the description covers most essentials: dependency on current reservation, need for confirm_action, and parameter sources. Could mention what happens if the new seat is unavailable or if confirm_action fails, but overall sufficient given no output schema.

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

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

Schema coverage is 100% with clear descriptions for both parameters. The description adds meaningful context: explains that new_seat_id can be obtained from recommend_library_seats or get_library_seat_status, and that mcp_session_id requires LIBRARY login. Also notes that charge_id is not needed. Significantly enhances 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 action: automatically return current library seat and change to a new seat. It distinguishes from sibling tool 'prepare_reserve_library_seat' by noting that this tool requires an existing reservation, while the sibling is for new reservations. The purpose is specific and unambiguous.

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

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

Explicitly states when to use this tool vs alternatives: 'If there is no current reservation, use prepare_reserve_library_seat.' Also specifies the requirement for mcp_session_id and that confirm_action must be called for final execution. Provides clear context on prerequisites and workflow.

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?

Beyond the readOnlyHint annotation, the description adds that it combines real-time seat status with a static catalog, explains how boolean preferences work (true=prefer, false=avoid, null/omit=no preference), and states that graduate-only rooms are excluded by default. This provides behavioral context beyond what annotations alone convey.

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 paragraph with multiple sentences, each contributing meaningful information. While not extremely compact, it avoids redundancy and front-loads the key purpose. It could be slightly more structured (e.g., bullet points) but remains 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?

Despite good coverage of usage and parameters, the description does not explain the output format or structure of recommendations, and lacks an output schema. Given the tool's complexity (10 params, no output schema), this omission reduces completeness for an agent trying to interpret 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?

The input schema already covers 100% of parameters with descriptions. The description adds value by clarifying the semantic role of boolean preferences and the default/conditional behavior of include_graduate_only, which supplements the schema's 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 clearly states it ranks available library seats based on user preferences, explicitly distinguishes itself as a read-only tool, and references the follow-up tool prepare_reserve_library_seat, differentiating it from sibling tools like get_library_available_seats.

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

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

The description provides explicit guidance: it explains when to use (for ranking with preferences), when not to (to filter by graduate status, use include_graduate_only), and specifies the correct next step (call prepare_reserve_library_seat after selection). It also details the semantics of boolean preferences with null meaning no preference.

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

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

Annotations already indicate readonly and non-destructive behavior. The description adds context about live fetching and fallback, which is useful but not detailed enough (e.g., what happens if both fail, response 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?

Two sentences: purpose first, then behavior for live parameter. No filler, every sentence earns its place.

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

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

Given no output schema, the description reasonably covers the tool's scope and behavior. Could mention output format or source fallback limits, but adequate for a search tool with annotations.

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

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

Schema coverage is 100% with clear parameter descriptions. The description adds minimal value beyond the schema, only clarifying the live parameter's effect. Baseline at 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 searches for academic policy paragraphs from official university sources. It names specific subdomains (regulations, graduation, scholarship) but does not explicitly differentiate from siblings like check_graduation_requirements or list_academic_policy_sources.

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 explains the live parameter behavior ('live=true queries official URL, fallback to seed corpus') but gives no guidance on when to use this tool versus alternatives for graduated or policy checks.

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?

Description discloses partial matching behavior on multiple fields (name, alias, location) and empty-query behavior. Annotations already declare readOnlyHint=true and destructiveHint=false, so description adds operational details without contradiction.

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

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

Description is concise: one sentence with two clear clauses, front-loaded with purpose and followed by behavior. 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 low complexity (1 optional param, no output schema), the description fully covers behavior, parameter semantics, and usage context. No gaps.

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

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

Schema coverage is 100% with description for 'query'. Description adds value by explaining partial matching across fields and full list on empty query, beyond schema's basic type and length.

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 searches for campus facilities (식당, 카페, 편의점, 서점) with specific verb '검색합니다'. It distinguishes from siblings by focusing on physical facilities, unlike other tools for notices, grades, etc.

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 facility search and mentions empty query returns full list, but does not explicitly state when not to use or compare to alternatives. However, the tool's focus is clear from 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?

Annotations already declare readOnlyHint=true. The description adds that the response includes title, author, call number, location, and availability, and that search matches partially on title/author/publisher. This provides useful behavioral context beyond the 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 concise—two sentences—and front-loaded with the main action. Every sentence adds value without redundancy.

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

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

Given the lack of output schema, the description lists response fields (title, author, call number, location, availability) and mentions partial matching. It covers the main functionality and constraints well for a search 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%, and the description does add any additional meaning beyond what the schema already provides for the parameters.

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

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

The description clearly states the tool searches for books in Soongsil University Central Library by keyword, listing the response fields. This is specific and distinct from sibling tools like search_campus_facilities and search_notices.

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

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

The description explicitly states the tool is read-only and that loan/reservation actions are handled by other tools, guiding when to use it and when not to. However, it does not name the alternative tools explicitly.

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

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

Annotations indicate readOnlyHint=true and destructiveHint=false, and the description adds valuable behavioral context: keyword search spans title and body, category filtering is available, and compact mode alters the response format. No contradictions with annotations.

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

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

The description is three concise sentences in Korean, with the purpose front-loaded. Every sentence adds essential information—search scope, category filter, and compact mode—without unnecessary 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?

Despite lacking an output schema, the description outlines the return format for both compact and non-compact modes (titles/URLs vs. with date/category). All four parameters are addressed, and the token limit for keyword is specified. It is sufficiently complete for an agent to use correctly.

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

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

Schema coverage is 100%, and the description adds meaning beyond the schema: it specifies that the keyword is searched in title and body, explains the category filter's effect, and clarifies the behavior of the 'compact' parameter. This provides the agent with clearer usage semantics.

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 searches Soongsil University notices by keyword, returning notices containing the keyword in title or body. It distinguishes itself from sibling tools like 'get_recent_notices' or 'get_active_notices' by focusing on keyword search. The mention of category filtering and compact mode further clarifies its scope.

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

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

The description explains that specifying a category limits search to that category, but it does not provide explicit guidance on when to use this tool versus alternatives like 'search_academic_policy_sources' or 'get_notice_detail'. The usage context is implied rather than explicitly stated.

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

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

Annotations declare readOnlyHint=true and destructiveHint=false. The description adds that the tool uses a 4.5 scale, excludes P/F credits, and requires mcp_session_id, providing valuable context beyond annotations. No contradictions.

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

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

The description is two sentences, front-loading the core purpose and then covering usage modes and constraints. 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?

The description explains parameters and usage well, but does not mention what the output looks like. Since there is no output schema, the agent is left to infer the result type, which reduces completeness.

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

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

Schema coverage is 100%, but the description adds semantic information on how parameters interact (ex: using plannedGradePointAverage with plannedCredits to compute expected GPA, or targetGpa to compute required average). This goes beyond the schema descriptions.

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

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

The description clearly states the tool simulates cumulative GPA based on authenticated student's academicRecord, using a specific university's grading scale. It distinguishes from sibling tools as the only GPA simulation tool.

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 explains two usage modes (with plannedGradePointAverage or targetGpa) and that both can be used together. It does not explicitly exclude alternatives, but the context makes clear when to use this tool.

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

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

Annotations show readOnlyHint=false and destructiveHint=false, which aligns with the description's indication of a non-destructive action (generating a URL). The description further explains the session ID reuse and creation behavior beyond what annotations provide.

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 yet comprehensive, front-loaded with the core purpose and followed by a clear numbered procedure. Every sentence earns its place.

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

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

Given no output schema, the description implicitly covers the return values (loginUrl and mcpSessionId) through the procedure. It fully explains the auth flow context and how to proceed after invoking the 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 good parameter descriptions. The description adds context by listing what each provider covers (e.g., SAINT for timetable/grades), which adds value beyond the schema.

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

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

The description clearly states that it generates a browser login URL for specified providers (SAINT, LMS, LIBRARY), which is a specific verb+resource. It distinguishes from sibling tools like get_auth_status, logout_all, etc.

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

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

Explicitly instructs to use when authentication tools return AUTH_REQUIRED, and provides a step-by-step procedure for the full auth flow, including not replacing the login URL.

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?

Beyond annotations (readOnlyHint false, destructiveHint false), the description reveals key behavioral traits: auto-reservation without confirm_action and background server worker execution, which are critical 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?

Two sentences efficiently convey the purpose, consent implication, auto-reservation, and prerequisite, 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 tool with 6 parameters and no output schema, the description covers the essential behavioral context and the mandatory session ID. It could mention success/failure indicators but remains adequate.

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

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

With 100% schema description coverage, the parameters are already well-documented. The description does not add new semantic detail beyond what the schema provides, meeting the baseline.

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

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

The description clearly states the tool registers a background wait intent for a library seat, distinguishes from siblings like 'cancel_library_wait' and 'prepare_reserve_library_seat' by highlighting the auto-reservation behavior without confirm_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?

It specifies the requirement for a library session ID and that the call itself is consent, providing clear context for use. However, it does not explicitly exclude alternative tools or give when-not-to-use guidance.

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