アーカイブ内リンク辿り（芋づる発掘）

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. It clearly states the core action (extract outlinks) and explains the intended recursive usage pattern, which adds context beyond the tool name. However, it does not disclose output format, failure conditions, or any limitations, leaving some transparency gaps.

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 three sentences: the first states the core function, the second provides strategic rationale, and the third specifies effective page types. Each sentence earns its place and the information is front-loaded, though the middle sentence is somewhat long and expository.

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 4 parameters and no output schema, the description adequately covers the 'why' and 'when' but omits details about what the returned data looks like or how pagination/limit behave. This leaves the agent without full expectations for the tool's outputs, so while sufficient for basic use, it is 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% for all 4 parameters, providing a baseline of 3. The description enhances parameter understanding by emphasizing that the 'url' should be a link collection page and that 'externalOnly' (default true) aligns with the goal of finding sites not indexed by search engines, thereby adding meaningful guidance beyond the schema's 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?

The description clearly states the tool's function ('extract external links from saved pages') and places it in the context of 90s-era site discovery via mutual links and web rings, distinguishing it from general search or page-fetching tools. This it unequivocally separates it from siblings like wayback_fetch_page or wayback_cdx_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?

Explicit guidance is given on when to use: it is described as the most powerful way to reach obscure old sites and is highly effective on link collection, web ring, antenna, and ranking pages. The description does not explicitly name alternative tools, but it contrasts with search engines and implies a strategy of iterative traversal, offering clear situational context.

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