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

Goes well beyond annotations: discloses cost model (pay per MB, failures not charged, pay per call in stablecoins), the 10 MB cap, truncation flagging, and header override behavior. Annotations only cover read-only/open-world; the description adds the pricing and payload-size behavioral context an agent needs.

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?

Two dense sentences, front-loaded with the core action and return shape, then method/headers/country, then the critical billing terms. Every clause carries load.

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?

Covers action, return shape, methods, limits, cost, and failure handling for a 6-param tool with no output schema. Minor gap: no explicit routing to the 'proxy' sibling or pagination/large-body retry guidance for a >10 MB response.

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 83%, so the schema documents most params. The description adds method set (GET/HEAD/POST), 'your own headers,' and 'optional country' in prose, but does not explain parameters the schema leaves undocumented or add syntax beyond it.

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 (fetch) and resource (one URL) with the differentiator that it goes through a residential IP and returns raw JSON. The sibling 'proxy' is implicitly distinguished by the 'raw response' framing, though not named explicitly.

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?

Says 'No JavaScript rendering,' which is a clear when-NOT-to-use-this signal (use a browser-rendering tool instead). However, it does not name or route to the sibling 'proxy' tool or state when to prefer one over the other.

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