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

Annotations already declare readOnly/openWorld/non-idempotent, and the description adds substantial non-obvious behavior: the backing model (Llama 3.3 70B in JSON mode), the 40,000-character source cap, that failures are not charged, the $0.03 USDC price via x402 or prepaid credits, and that it is excluded from the free trial. That is meaningful operational context beyond the annotations.

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?

Front-loaded with the core action and inputs, then use cases, then billing constraints — efficient and scannable. Minor redundancy in repeating the $0.03 price already present in the title, 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?

With an output schema present, return format need not be explained, and the description covers everything else an agent needs: accepted inputs, size limit, model, pricing, payment paths, failure billing, and trial exclusion. Complete for a paid extraction endpoint.

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% (baseline 3), and the description adds real meaning by expanding what 'url' accepts (web page, PDF, Word, Excel) and restating the 40,000-character source limit. It does not explain the 'instructions' parameter's role beyond what the schema already documents.

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 ('AI structured extraction' producing 'JSON that fits' a caller-supplied schema), which is far more precise than the generic sibling 'extract'. The mechanism (source in, schema-shaped JSON out) makes the tool's identity unambiguous even without naming a sibling.

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?

Gives clear positive context via concrete use cases ('prices, contacts, specs, events, invoices and tables') and the input mode ('give a URL ... or text'), which tells the agent when this fits. It stops short of explicit when-not guidance or naming an alternative sibling (e.g. extract, metadata), so no exclusion criteria are provided.

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