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

Annotations declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds rich behavioral context: 'deterministically judge' aligns with idempotency; explains returned verdict types (eligible/ineligible/needs_more_info/manual_review) and the follow-up loop; discloses that free-text conditions are returned as manual. 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 slightly wordy (e.g., 'the KILLER feature') but well-structured. It front-loads the purpose and follows with usage flow. Nearly every sentence adds value, though it could be trimmed slightly without loss.

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, output schema exists, sibling tools), the description covers all essential aspects: how to invoke, what the response includes (verdicts, missing_info questions), and how to drive a follow-up loop. It is complete for an agent to use effectively.

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

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

Schema has 0% description coverage. The description compensates fully by explaining the role of each parameter: policy_id (required), profile (inline with optional fields like age, region, income, etc.), and user_key (restores remembered profile). It adds meaning beyond the schema's generic object type.

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 eligibility for a specific policy (by policy_id) and distinguishes it from siblings like search_youth_policies (search), get_policy_detail (detail), and profile management tools. The verb 'judge' and resource 'eligibility for a policy' are 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?

The description provides detailed guidance: use inline profile or user_key, interpret verdicts, handle missing_info by asking questions and saving with remember_user_profile, then re-running. It implicitly guides when to use this tool vs. siblings by referencing remember_user_profile, but does not explicitly state when not to use it.

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

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

Annotations already declare readOnlyHint and destructiveHint. The description adds valuable behavioral details: API source, client-side filtering, requirement of a key, and return fields. 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?

The description is well-structured with purpose first, then details. At 6-7 sentences, it is lengthy but each sentence adds value. Minor redundancy could be trimmed.

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 3 optional params and output schema, the description covers source, filtering, usage timing, and return fields. No gaps given annotations and 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 has 0% coverage, so description carries full burden. It explains region format (e.g., '서울', '경기 수원') and keyword as free-text. It does not detail limit, but given simplicity, it's adequate.

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

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

The description clearly states the tool finds nearby Korean youth centers for offline help, specifying the resource type and context (after policy matching). It distinguishes from sibling tools like search_youth_policies by emphasizing in-person guidance.

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

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

The description explicitly says when to call: when the user wants face-to-face guidance or asks for nearby help. It mentions it's after policies are matched. No explicit when-not, but context makes it clear this is not for policy search.

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, openWorldHint, idempotentHint, destructiveHint. Description adds value by detailing return fields (support content, application period, etc.) and usage context. 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?

Single sentence front-loaded with Korean name, then English explanation and usage hint. Every word serves a purpose.

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

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

Given output schema exists, description doesn't need to detail returns. It covers purpose, usage context, and expected detail types completely for this simple read-only 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?

Only param policy_id has no schema description, but description clarifies it's the policy identifier from search_youth_policies, adding meaning beyond the schema type.

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 full application details for a specific policy by policy_id, listing content types (support content, application period, etc.) and distinguishes from sibling search_youth_policies by specifying call this after user picks a 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?

Explicitly says when to use: after user picks a policy and wants application details. Does not explicitly state when not to use or compare with siblings, 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?

Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the tool is safe. The description adds behavioral context: returns most recent notes on empty query and uses 'contextual retrieval.' No contradictions with annotations. Slightly above baseline due to added 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?

The description is two sentences plus a functional label, no filler. Every sentence adds value: first states purpose, second provides usage guidance. Well-structured and front-loaded.

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

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

Given the tool has three parameters and an output schema, the description fails to explain k and user_key parameters. While annotations cover safety and output schema may handle return values, the missing parameter documentation leaves the agent underinformed. The description is adequate but not complete for effective 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 0%, so the description must compensate but does not. It fails to explain parameters k and user_key, and only indirectly hints at query by saying 'an empty query returns the most recent notes.' User_key is mentioned but not defined as a parameter. The omission of parameter meaning is a significant gap for a tool with three 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's purpose: 'recall a user's previously saved situation/preferences relevant to a query, via contextual retrieval.' It provides a specific verb and resource, and distinguishes itself by focusing on personalization for policy recommendations. However, it does not explicitly contrast with all sibling tools, such as search_youth_policies, leaving some ambiguity.

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

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

The description offers clear usage guidance: 'Call this before recommending policies or judging eligibility to personalize' and 'an empty query returns the most recent notes.' It also specifies to use the same user_key as when saving. While it does not list when not to use the tool, the guidance is sufficient for typical scenarios.

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 mutation (readOnlyHint=false) but not destructive. The description adds context: data is for eligibility judging, user_key must be stable and agent-controlled. 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?

Description is 3-4 sentences, front-loaded with purpose. Minor redundancy with Korean translation in parentheses, but overall concise and scannable.

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 presence of output schema (not shown) and annotations, description adequately covers usage context, parameter guidance, and relationship to sibling tool check_eligibility. Missing error handling but sufficient for a simple storage 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 0%, but description explains 'note' as a short note with examples and 'user_key' as a stable per-user identifier that the agent controls. This adds significant meaning beyond the schema's string type.

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 stores user's durable facts (age, region, income, etc.) for later personalization and eligibility checking. It distinguishes from sibling 'recall_user_profile' by focusing on remembering, not retrieving.

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 'Call this whenever the user reveals a durable fact about their age, region, income, employment or education'. Indicates use case and connection to check_eligibility, providing clear when-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?

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds context about fusing data sources (curated corpus + open API) and the return structure including eligibility criteria, which enhances understanding 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 front-loaded with purpose, data sources, and usage. Every sentence is informative, though slightly verbose; could be trimmed slightly without losing clarity.

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

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

Given the tool's complexity (Korean policies, two data sources, 4 parameters, output schema), the description is comprehensive: it covers usage triggers, data fusion, result structure, and next-step recommendations.

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

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

Schema coverage is 0%; description explains query, region, and category purpose but does not detail the 'k' parameter or format constraints for region/category. Some compensation but incomplete.

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 Korean youth policies and subsidies by free-text query, with optional region and category. It explicitly names example queries like '월세 지원' and distinguishes from sibling tools such as 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?

Explicitly says 'Call this when the user asks what youth policies or support money they could get, or searches by topic' and instructs to follow up with check_eligibility for qualification checking, providing clear guidance.

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