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

Annotations only cover read-only and open-world, but the description adds substantive context: text-only output with no images, the shape of what comes back, and the pay-per-call model ($0.05 USDC via x402, waived with an API key). It omits failure behavior typical of Tor fetches (timeouts, unreachable onions, retries), which is a meaningful gap for an unreliable network path.

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?

Three front-loaded sentences: what it does, what the alternate input does, then cost/auth. No filler, though the pricing clause is dense and could be split or moved to a note for easier scanning.

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?

With one parameter, no output schema, and full schema coverage, the description covers mode, output fields, and commercial terms adequately. Missing only the operational caveats an agent would want before relying on it — latency, failure modes on unreachable onions — which keeps it below a 5.

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% and the single parameter is already documented, so the baseline is 3. The description goes further by explaining the semantic consequence of the URL value — a clearnet URL switches the tool into an onion-address-harvesting mode — which is real meaning beyond the schema text.

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?

States a specific verb and resource ('Fetch a .onion page over Tor') plus the exact return payload (status, title, visible text, links), and adds a second distinct mode for clearnet URLs. This clearly separates it from the generic sibling http_get, which does not route over Tor or extract .onion addresses.

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 two modes are stated explicitly with their triggering input ('.onion URL' vs 'clearnet URL'), which is enough to select behavior correctly. It stops short of naming alternatives or exclusions (e.g., 'use http_get for normal pages'), so an agent must infer that http_get is the wrong pick for .onion targets.

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