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

With only readOnlyHint/openWorldHint in annotations, the description carries the load well: 12,000-character text cap, 20-field schema cap, 500-char instructions cap, null-filling for absent values, model identity, one retry on non-JSON output that is not charged, and the exact $0.004 USDC/x402 payment terms with the supported chains. These are genuinely non-obvious operating and cost facts an agent must plan around.

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?

Purpose and mechanism are front-loaded, and the trailing clauses (retry policy, pricing, payment rails) each earn their place for a paid, metered tool. It is one dense paragraph with no formatting breaks, which makes the operational details slightly harder to scan, but there is no filler.

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 paid, open-world, loosely-typed tool with an output schema, the description covers inputs, input limits, output shape, failure/retry behavior, and cost. Nothing an agent needs to decide to call it and to predict its behavior is missing, even though the output schema already documents return shape.

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 baseline is 3, and the description adds real meaning on top: the schema parameter is bounded at 20 fields and its values drive null-filling in the output, text is capped at 12,000 chars, and instructions at 500. It is the output-coupling of the schema param that pushes it above baseline.

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 transformation (arbitrary user-supplied field schema in, exactly-matching JSON object out) over two named input sources (url or own text). That 'user-defined generic schema' framing separates it from the fixed-purpose extraction siblings such as invoice_extract, resume_parse, entities and tables without needing to name them.

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 context is explicit ('from a web page (url) or your own text', text 'instead of url'), so an agent knows the two invocation modes and their exclusivity. It stops short of naming alternatives or stating when not to use it (e.g., for invoices/resumes where a dedicated sibling exists), so it lands at clear-context-without-exclusions.

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