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

Annotations already declare read-only/idempotent/non-destructive, and the description adds substantial context they cannot carry: 16K char cap, max 10 fields, list-mode array semantics, $0.05 per call over x402, prepaid x-credit-token header for unlimited calls, and no free tier. Payment and quota behavior is exactly the kind of trait an agent needs before invoking.

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?

The core transformation leads, followed by the highest-value mechanics (fields, list), limits, and the batch/pricing routing. It is dense and information-packed rather than padded, though the promotional framing ('ANY', 'guaranteed-valid') and stacked pricing sentences cost it a point.

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?

An output schema exists so return values need not be described, and for a 3-parameter read-only extraction tool the description covers inputs, limits, cost, auth header, and the batch alternative. Nothing an agent needs to call it correctly is missing.

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?

With 100% schema coverage the baseline is 3, but the description genuinely enriches the parameters: fields is capped at 10 and comma-separated, and list=true means 'extract EVERY repeated record as an array' rather than a single object. That 'true vs absent' distinction materially changes the call and is not spelled out in 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?

States a concrete verb+resource transformation ('Unstructured text → structured JSON') and names the output guarantee (schema-enforced JSON). It also distinguishes itself from siblings by explicitly denying a crypto-specific scope and pointing to ai-extract-batch for the multi-document case, so an agent can place it without opening the schema.

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 concrete usage contexts ('pages, emails, receipts, logs') and names the alternative for a different condition ('Many documents? ai-extract-batch'). It stops short of an explicit when-not-to-use statement beyond that routing hint, keeping it below the top band.

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