reach

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

With no annotations, the description carries the full burden and does so richly: it names the retrieval cascade, the return fields (ok, markdown, tried, error with code/message/next_steps), the mirror-vs-Wayback fallback and the `archived` capture time, and that cached=true issues no network request. It does not address permissions, rate limits, or whether any state is mutated, which are the remaining gaps for a network-fetching tool.

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 purpose is front-loaded in the first sentence and every following clause carries behavioral information (return shape, mirror, fallback, cache semantics) with little filler. It is dense and somewhat run-on, and jargon like 'winner-first' and 'detail sub-pages' costs a little clarity without being wasteful.

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?

There is no output schema and no annotations, so the description correctly takes on the job of describing return values and fallback semantics, which it does well. The main shortfall for a five-parameter tool is the unexplained `want` parameter and the absence of any auth or rate-limit context.

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 explains three of five parameters inline (full=true for full markdown, fresh=true to re-read, cached=true for no-request mirror reads), but `url` and especially `want` (default "") are left entirely undefined in both schema and description. Partial compensation for a real coverage gap.

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 states a concrete action on a concrete resource: fetch one page and judge whether it is good information, then names the internal retrieval strategies it tries (learned readers, url rewrites, detail sub-pages). This is distinguishable from purpose-level siblings like site_map or cache, though it never explicitly routes away from its closest sibling, scout. The idiosyncratic verb 'reach' is only clarified by the body text rather than the opening clause.

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?

Usage is implied rather than stated: cached=true 'sends no request' and fresh=true re-reads, which tells the agent about modes but not when to pick this tool over scout or site_map. Automatic fallback behavior (wall/hold → Wayback) is described, but there is no when-not guidance or explicit alternative named for the general case. An agent can infer the single-page-fetch role, but must infer it.

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