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

Annotations already cover readOnly/openWorld/non-destructive, and the description adds material context beyond them: typical latency of 1–3 seconds, JSON output, restriction to read-only public pages, an explicit no_recipe failure mode with candidate list and best_guess, and a prompt-injection warning to treat page content as data rather than instructions.

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?

One dense, front-loaded paragraph: capability and latency first, then examples, then failure handling, then the safety caveat. The examples are long but earn their place by demonstrating the natural-language task format; a little tightening is possible but nothing is wasted.

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 a free-form nested params object and no output schema, the description covers the important unknowns: latency, output type, read-only scope, and the error path. It does not describe the shape of a successful JSON response, though that is inherently site-dependent.

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%, so the schema already documents task, site, country and params. The description only adds the framing that Wield selects the recipe and fills its params, with user-supplied params overriding the guess — useful context, but nothing about formats or constraints beyond the schema.

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 verb and resource — perform a task on a real website and return its data as JSON — and backs it with four varied example tasks that show the expected input shape. It also distinguishes itself from siblings by naming find_recipe and request_recipe as the fallback path.

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 when-to-use (a describable task on a known site) and an explicit failure branch: if no recipe fits, nothing runs, you get no_recipe with candidates and a best_guess, then try find_recipe or request_recipe. The alternatives and the condition that selects them are spelled out.

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