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

With no annotations, the description discloses key behaviors: does not fill empty sections arbitrarily, marks missing content, auto-checks checklist, diagnoses page volume, and appends unknown chart kinds. Missing details on return format or side effects.

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

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

The description is concise and front-loaded, with every sentence adding value. No redundant or irrelevant phrases.

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 with sections, charts, checklist, and page diagnosis, the description covers the main functionality but omits details on how the checklist works or how page target is used. Still sufficient for an agent to understand the tool's role.

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 meaningful context: sections should be draft_section results, grant_id is only for context and not to fabricate facts, and charts not in catalog go to appendix.

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 explicitly states it assembles PSST sections and charts into a full business plan markdown in government format, clearly distinguishing from sibling tools like draft_section (which drafts individual sections) and plan_outline.

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

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

The description advises passing draft_section results directly for sections, and notes handling of empty sections and unknown chart kinds, but does not explicitly contrast with alternatives or provide when-not-to-use guidance.

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

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

With no annotations, the description carries full burden. It discloses that sales figures are not filled arbitrarily and must be provided by the entrepreneur. It also mentions integration with a knowledge base for funding bridges. However, it does not describe side effects, authorization needs, or the exact output format beyond SVG, limiting transparency.

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

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

The description is concise, containing all necessary information in a single paragraph without redundancy. It is front-loaded with the core purpose. Minor improvement could be structure with bullet points, but it remains 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?

Despite no output schema, the description covers key output elements (market change descriptions, SVG diagram) and behavioral constraints (no arbitrary sales figures). It is adequate for a complex tool, though some details like pagination or error handling are missing.

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

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

Schema coverage is 100%, so the description adds value by explaining the purpose of key parameters: '과거준비' as proof of capability, '미래계획' requiring causal chains, and '자금계획' as funding bridges. This context goes beyond the schema's basic descriptions, enhancing semantic 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 explicitly states that the tool generates a roadmap connecting milestones across four axes (Item, Funding, Marketing, Operations) as causal chains, not just timelines. It also specifies inclusions like funding bridges, market change descriptions, and an SVG diagram, clearly distinguishing this from generic planning tools among its siblings.

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

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

The description does not provide any guidance on when to use this tool versus alternatives like assemble_plan or plan_outline. No context about prerequisites, constraints, or typical use cases is given, leaving the agent to infer suitability.

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

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

No annotations provided, so description carries full burden. It discloses deterministic rule-based checks, output types (적합/확인필요/부적합), includes a disclaimer about not guaranteeing eligibility and final confirmation by operating agency. This is fairly transparent.

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

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

Two sentences: first clearly states purpose and criteria, second describes output and disclaimer. No wasted words, front-loaded with key information.

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

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

Given the nested input schema and no output schema, the description covers output structure (three levels with evidence and actions) and includes a necessary disclaimer. It is sufficiently complete for a deterministic check, though could mention side effects or limitations more explicitly.

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 50%. The description adds meaning by listing the criteria categories checked (창업여부, 업력, 지역, etc.) for the profile parameter, beyond what the schema provides. This helps the agent understand how the profile is used.

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 tool checks eligibility for a specific grant using deterministic rules, lists criteria, and describes output (적합/확인필요/부적합 with evidence and actions). This clearly distinguishes it from siblings like recommend_grants or score_application.

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

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

The description implies usage context (checking self against a specific grant) and lists criteria, but does not explicitly state when to use versus alternatives or when not to use. Sibling names provide context, so it is clear but lacks exclusions.

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

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

With no annotations provided, the description effectively discloses behavioral traits: it structures facts into a draft, marks missing facts as '[입력 필요]', does not fabricate information, and returns a zero-point answer warning. It also specifies the output format. This goes beyond basic functionality, though it does not mention authorization or side effects.

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

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

The description is a single sentence that efficiently conveys the main action and outputs. It front-loads the core purpose and is not overly verbose. However, the sentence is somewhat dense; a more structured format (e.g., bullet points) could improve readability without losing conciseness.

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

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

Given the tool's complexity (2 parameters, one with enum, nested object inputs) and no output schema, the description is complete. It explains inputs, processing rules (no fabrication, marking missing inputs), and outputs (summary, structured body, warning, diagrams). No critical information is omitted.

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

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

Both parameters are documented in the schema (100% coverage), and the description adds meaning: it explains the 'section' enum values explicitly and describes 'inputs' as key-value pairs with concrete examples (e.g., {문제:'...', 시장현황:'...'}). It also clarifies how missing inputs are handled ('[입력 필요]'), 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 the tool's purpose: creating a draft for a PSST section based on founder-provided facts. It specifies the four section keys (P, S1, S2, T) and their meanings, and lists the return outputs (summary, structured body, zero-point warning, recommended diagrams). This distinguishes it from sibling tools like plan_outline or market_research.

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

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

The description implies the tool is used when a founder provides facts and needs a structured draft. However, it does not explicitly state when to use this tool versus alternatives, nor does it provide when-not-to-use guidance or list prerequisites. The context is clear but lacks exclusions or comparisons to 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?

With no annotations provided, the description carries full burden for behavioral disclosure. It explicitly states that it returns only actual collected announcements with source and collection time, and that it does not fabricate data. This adds significant transparency beyond the input schema, though it omits details like authorization needs or rate limits.

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

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

The description is two sentences with no wasted text. The first sentence states the search capability and filter dimensions, the second clarifies data authenticity. It is front-loaded and every sentence earns its place.

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

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

Given the complexity of the tool (6 optional parameters, no output schema), the description mentions that results include source and collection time, giving some return format context. However, it does not specify default behavior when no parameters are provided or elaborate on result structure. Slightly incomplete but still informative.

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

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

The input schema covers 100% of parameters with descriptions, so baseline is 3. The main description lists filter categories (keyword, region, stage, field, deadline) but does not add additional meaning beyond what the schema already provides for each parameter. No parameter-specific guidance is added.

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 ('검색합니다' - searches) and explicitly states the resource ('정부 창업지원 공고' - government startup support announcements). It distinguishes itself by clarifying it only returns real collected announcements, preventing hallucination, which differentiates it from sibling tools like recommend_grants that might provide suggestions.

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 searching announcements but does not provide explicit guidance on when to use this tool versus alternatives like recommend_grants or check_eligibility. No when-not-to-use or context exclusions are provided, leaving the agent to infer the appropriate scenario.

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

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

Without annotations, the description discloses estimation uncertainty (1100-1600 characters per page, actual may differ) and partial output when character count is missing. It does not indicate any destructive behavior, but lacks clarity on side effects or authentication needs.

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

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

The description is two sentences long and front-loads the main purpose. The first sentence is slightly dense with multiple items, but overall efficient and without redundancy.

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

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

Given no output schema, the description provides sufficient context for return values (suggestions, shortcuts, principles) and clarifies partial output. It covers the three parameters adequately and addresses estimation accuracy.

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 describes all parameters with full coverage (100%). The description adds no new semantic details beyond what the schema covers, so baseline 3 is appropriate.

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

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

The description clearly states the tool diagnoses page volume for HWP business plans, provides adjustment suggestions, shortcut tables, and readability principles. It specifies the resource (HWP plan) and action (diagnose, provide), distinguishing it from siblings like assemble_plan or build_roadmap.

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 HWP document formatting and volume assessment, but does not explicitly contrast with siblings or state when not to use. No alternative tools are mentioned.

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

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

No annotations are provided, so the description carries the full burden. It discloses that the tool does not fabricate data, marks missing entries, and auto-generates a radar chart if conditions (3+ axes, all numeric) are met. This adds significant behavioral context beyond the schema. However, it does not mention potential side effects or modification of inputs.

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

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

The description is two sentences, front-loaded with the core outputs, followed by constraints. Every sentence adds essential information with no redundancy 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?

The description covers the tool's purpose, data input behavior, and auto-generation features. Given the complexity (6 parameters, nested objects) and no output schema, it is reasonably complete. It does not address all edge cases (e.g., handling of invalid input), but it provides sufficient context for typical use.

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

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

Schema description coverage is 100% with detailed descriptions for most parameters. The tool description adds value by explaining auto-generation of radar charts based on '비교축' conditions and the '[입력 필요]' behavior for missing fields, which goes beyond the schema. This justifies a score above the baseline of 3.

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

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

The description explicitly states it provides PEST analysis, TAM/SAM/SOM/LAM market size estimation, competitor comparison table with radar charts. The verb '제공합니다' (provides) indicates the tool generates these outputs, clearly distinguishing it from sibling tools like plan_outline or draft_section.

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 guidance: data must be input by the founder, missing items are marked as '[입력 필요]', and sources must be verified. It implies the tool is for founders to input their own data. However, it does not explicitly state when to use this tool versus alternatives, e.g., when not to use it.

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

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

No annotations provided, so description carries full burden. Mentions 'does not fabricate founder facts'—a positive behavioral trait. However, lacks details on side effects, permissions, or what the tool does not do (e.g., no full plan generation).

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 delivers main purpose upfront, second adds conditional behavior and inclusions. No wasted words; 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?

No output schema, so description must hint at return format. Mentions inclusions (diagrams, principles, checklist) but not structure. Could better explain integration with sibling tools, but sufficient for a generation 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%, so baseline is 3. Description adds context for grant_id (conditional notes) but does not elaborate on other parameters beyond what schema provides. Adequate but not exceptional.

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

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

Clearly identifies action ('generates') and specific output ('4-section skeleton for PSST framework'), with distinct sections named. Implicitly distinguishes from siblings like 'draft_section' and 'build_roadmap' by focusing on skeleton generation.

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 clear context on when to use (with or without grant_id) and what customizations occur. Lacks explicit exclusions or comparison to alternatives, but usage is well implied.

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

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

With no annotations provided, the description bears full responsibility. It discloses that the tool auto-detects specific patterns (zero-score answer patterns, qualitative comparisons, paragraph summaries) and flags remaining items as 'checkneeded'. It mentions including warnings and a score for reference. However, it doesn't specify whether the tool is read-only, if it modifies the input, or the exact format of the output. The behavioral scope is moderately transparent but could be more precise.

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 paragraph that front-loads the main action. Every sentence adds value, though the information is dense. It could benefit from bullet points for readability, but it remains efficient and avoids verbosity.

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

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

The complexity is moderate (2 params, no output schema, no annotations). The description explains the tool's purpose and detection capabilities, but lacks details on the output format, prerequisites (e.g., language), and limitations. Since there is no output schema, the description should provide more context on what the agent will receive, but it does hint at warnings and scores.

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 repeats the schema's note that fullText can be used instead of sections, but does not add deeper meaning beyond the schema. No parameter-specific details are provided that would help the agent interpret values 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 checks a business plan against a 10-item checklist of absolute rules, automatically detecting specific patterns and providing warnings and scores. The verb '점검합니다' (checks) and resource '사업계획서' (business plan) are specific, and the mention of '절대 규칙 체크리스트 10항목' distinguishes it from sibling tools like score_application or check_eligibility.

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

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

No explicit guidance on when to use this tool versus siblings. There is no mention of alternatives or when not to use it. The description implies usage for checking against the 10 absolute rules, but lacks direct context like 'use this to verify compliance with the checklist; for eligibility checks, use check_eligibility instead.'

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

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

With no annotations, the description discloses key behaviors: automatic exclusion of closed announcements, fallback list and input-needed guidance for empty input, reliance on collected announcements with source and reference point, suitability as a reference only, no fabrication of facts, and marking missing items as '[Input needed]'. This provides rich transparency beyond basic functionality.

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. In two short paragraphs, it conveys purpose, inputs, behavior, limitations, and fallback handling. Every sentence adds value without redundancy or 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 output schema, the description should explain the return structure. It mentions ranking score (0-100) and fallback list but does not specify the output format (e.g., list of grants with scores, fields included). Also, it does not mention how the 'limit' parameter affects results. The description is adequate but lacks output details for full 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?

All 6 parameters have good descriptions in the schema (100% coverage). The description groups them as profile inputs but does not add significant extra meaning beyond the schema. It mentions ranking based on these inputs but does not detail how each parameter affects the ranking. Baseline score of 3 is appropriate since schema covers semantics adequately.

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

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

The description clearly states that the tool recommends store announcements ranked by suitability (0-100) based on entrepreneur profile inputs. It explicitly mentions keywords, region, stage, industry, and deadline as inputs, and distinguishes itself from siblings like find_grants by focusing on ranking and automatic exclusion of closed announcements.

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 tool's functionality and when to use it: when you need a ranked list of suitable grants based on a profile. It mentions handling of empty input and automatic exclusion of closed announcements. However, it does not explicitly state when not to use this tool or suggest alternatives among siblings like check_eligibility or score_application.

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

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

With no annotations, the description bears full burden. It discloses that the tool only generates questions, does not fabricate facts, and marks provided info. It could add more about rate limits or auth, but the core behavior is well explained.

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

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

The description is concise, front-loads the purpose, and each sentence adds information. Could be slightly more structured but is 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?

No output schema, so return value details are limited. The description says it generates questions but does not specify format or structure. Adequate but not fully 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 value by explaining grant_id adds grant-specific questions and provided marks questions, which 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?

Description clearly states the tool provides a list of required factual items for business plans by PSST sections, and can incorporate grant-specific questions. It uses specific verbs '안내합니다' and '생성합니다', but does not explicitly differentiate from sibling 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 implies usage before writing a business plan and for startups, but does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states deterministic behavior (no randomness), maps to a rubric, and returns specific outputs. It also includes a caveat about reference use, which adds transparency beyond a simple functional description.

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

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

The description is two sentences long, well-structured, and front-loaded with the core purpose. Every sentence provides meaningful information without unnecessary words or redundancy.

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

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

Despite having no output schema, the description adequately explains the return values (total score, item scores, deduction reasons, etc.). It addresses the tool's complexity with 3 parameters (one nested object) and provides a caveat about reference use, making it complete for agent invocation.

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

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

Schema coverage is 100%, so the schema already documents all parameters and their types. The description adds marginal value by explaining that the tool maps to a rubric and returns scores, but it does not provide additional syntax or format details beyond what the schema offers. 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 deterministically scores a business plan summary by mapping it to a rubric (no randomness). It specifies that it returns total score, item scores, deduction reasons, improvement points, and next edit suggestions, distinguishing it from sibling tools like 'plan_review' or 'draft_section'.

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 notes that the tool is for reference and may differ from the final evaluation ('참고용이며 운영기관 최종평가와 다를 수 있습니다'), but it does not explicitly state when to use this tool versus alternatives like 'check_eligibility' or 'plan_review'. The usage context is implied but lacks exclusions or explicit guidance.

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

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

With no annotations, the description should compensate but only mentions it provides suggestions and is for reference. It does not disclose whether the tool is read-only, if it modifies data, or any side effects. The advisory tone hints at non-authoritative behavior but is insufficient.

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

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

The description is two sentences, front-loaded with the main purpose, and includes a necessary caveat. No wasted words, 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 complexity (3 parameters with nested objects, no output schema, no annotations), the description is too brief. It lists outputs but does not specify format or behavior, leaving the agent with insufficient context for proper invocation.

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

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

Schema description coverage is only 33%, leaving many nested fields undocumented. The description does not explain the parameters or their roles beyond 'based on announcement and profile', failing to add meaning beyond the schema.

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

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

The description clearly states the tool provides recommendations based on announcement and profile, listing specific outputs (track, points plan, emphasis, schedule, checklist). However, it does not differentiate from sibling tools like check_eligibility or recommend_grants.

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

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

No explicit guidance on when to use this tool versus alternatives. The description includes a caveat that it's a reference suggestion and advises verification, but does not specify contexts or exclusions.

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