check_recency

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

With no annotations, the description carries full burden. It discloses the markdown table format requirements, CSS selector syntax, the behavior when selector is empty (returns a specific string without network attempt), and the JS-rendered case. It also mentions the return format, making behavior 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?

The description is a few sentences, front-loaded with the core purpose, and includes necessary operational details without excessive length. It is well-structured and easy to parse.

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 that reads a file and checks recency, the description covers input format, edge cases (empty selector, JS-rendered), and return structure. However, it leaves parameter semantics for timeout and stale_after_months unexplained, and does not describe possible values of '판정' (judgment) field, though an output schema may cover that. Slightly incomplete but 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?

Schema coverage is 0%, so description must compensate. It explains cache_file format in detail (markdown table with URL and selector columns, case-insensitive, Korean/English allowed). However, it does not explain timeout or stale_after_months beyond their names, leaving ambiguity about meaning and units. Partial compensation only.

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 reads a markdown table file containing URLs and CSS selectors, extracts text from each URL via the selector, interprets it as a date, and judges recency based on stale_after_months. This is a specific verb+resource and distinguishes from siblings like check_links and update_page_cache.

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 explicitly explains when the tool cannot be used (empty selector or JS-rendered content) and instructs the agent to use update_page_cache after browser inspection. It doesn't explicitly compare with check_links, but the distinct purpose makes usage clear.

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