Seoul Tourism (Visit Seoul)

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

Annotations already declare readOnlyHint=true, indicating safe read operation. The description adds the behavioral detail that if the requested language version is unavailable, it falls back to Korean. 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 two sentences: the first states the main purpose and lists example data fields, the second adds language fallback behavior. No unnecessary words, front-loaded with critical 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 no output schema, the description lists typical fields (operating hours, address, contact, images, schedule) and explains language handling. This is sufficient for an agent to understand the tool's response structure and behavior.

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

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

Schema description coverage is 100%, so the schema already documents both parameters. The description adds the fallback behavior for language, which is not in the schema, providing extra semantic value beyond enum values.

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

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

The description clearly states the tool retrieves detailed information (operating hours, address, contact, images, schedule) using a content ID from search results. It specifies the resource (content ID) and verb (retrieve detail), distinguishing it from sibling tools like search_contents (which returns a list) and get_sync_status.

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 search_results have been obtained, but does not explicitly exclude alternative uses or compare with sibling tools. It provides clear context (retrieve detail for a specific content ID) but lacks explicit 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?

Annotations mark readOnlyHint=true, matching the read nature. Description adds specifics on what status includes (time, count, errors). 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 concise sentences, front-loaded with purpose and usage example. 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?

Lacks output schema, but describes return fields (sync time, count, errors). Minor gap in structure, but adequate for a simple status check.

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 both parameters with descriptions (100% coverage). The tool description adds no extra meaning beyond the schema, meeting 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 checks sync status of Visit Seoul data, specifying elements like last sync time, count, and errors. It distinguishes from sibling tools (get_content_detail, search_contents) which handle content details and search.

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

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

Provides an example query ('When was data updated?') to illustrate use case. Though no explicit when-not or alternatives are given, the context is clear enough for an AI agent.

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 the readOnlyHint annotation, such as when the period filter is valid (mainly for festivals), and provides retry strategies for region and keyword parameters when results are few. This helps the agent understand tool behavior without contradicting 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 paragraph but tightly written. It starts with the primary purpose, then usage context, then lists filters, and notes a constraint. Every sentence adds information; no filler. It is highly 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?

The description covers all input filters with clear descriptions, explains when to use them, and provides retry guidance. However, it lacks explanation of the output format (e.g., list of items with fields) and pagination behavior beyond the page parameter. Given no output schema, some return details would improve completeness, but it is sufficient 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?

With 100% schema description coverage, the baseline is 3. The description goes beyond by providing additional guidance: region accepts Korean or Roman characters and suggests retry logic, keyword should match search language, and period filter applicability. This 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 searches Seoul tourism content with specific categories and filters, and distinguishes it from sibling tools (get_content_detail for details, get_sync_status for sync). It gives concrete examples of queries, making the purpose unmistakable.

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 when to use this tool (for queries about Seoul festivals, attractions, restaurants, shopping, accommodation) and provides example queries. While it does not explicitly mention when not to use or alternatives, the context implies using get_content_detail for specific items. This is clear but lacks explicit exclusions.

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