check_links

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

With no annotations, the description carries the full burden of behavioral disclosure, and it delivers substantial insight: the tool runs in parallel, performs body-content analysis in addition to status-code checks, and explains the default Korean public-institution error indicators and how to customize them. It does not explicitly define edge-case behavior such as what counts as 'ok' on network errors or how timeout/max_workers affect results, but the core non-obvious algorithm is well exposed.

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 and economical: a one-line summary, a brief explanation of the underlying problem (fake 200s), a short bullet list for two key parameters, and a one-line return format. Every sentence earns its place and the main action is front-loaded before the explanatory paragraphs.

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 is highly complete for a read-only link-checking tool: it explains the true behavior, gives configuration guidance for error indicators, and provides the return shape. It does not further define the meaning of each return field (e.g., what 'ok' and 'error' represent) nor describe timeout/max_workers semantics, but the output shape and defaults are visible in the schema, leaving only minor 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 description coverage is 0%, so the description must compensate. It does so for the two most nuanced parameters: use_default_indicators (toggle off to avoid cross-domain false positives) and error_indicators (add site/task-specific phrases). The urls parameter is implied by the phrase "URL 목록". However, timeout and max_workers are left entirely to the schema, and no explicit behavior is described for them, though their names and defaults are reasonably self-explanatory.

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 opens with a specific action: "URL 목록의 접속 가능 여부를 병렬로 확인한다" (checks the accessibility of a URL list in parallel). It further clarifies the purpose by explaining that it not only uses HTTP status codes but also inspects page content for known error phrases, distinguishing it from a naive link checker. This clearly differentiates it from sibling tools like check_recency 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?

The description provides clear context for when this tool is appropriate: checking URL accessibility, especially when a CMS falsely returns HTTP 200 for nonexistent paths. It also gives usage guidance for the indicator knobs, such as setting use_default_indicators=False to avoid false positives in other domains, and adding error_indicators for site-specific phrases. However, it does not explicitly mention when to prefer check_links over check_recency or update_page_cache, so it stops short of a full exclusions statement.

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