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

Annotations already mark the tool as read-only and idempotent, and the description adds substantial behavioral context: guaranteed-valid structured outputs, exact-key behavior, list extraction semantics, character limits, pricing model, and authentication requirements (x-credit-token header, no wallet/API key). No contradiction with 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?

The description is dense but every sentence earns its place: purpose, parameter usage, list behavior, size limit, sibling routing, pricing, and auth are all relevant for an agent. It is front-loaded with the core value proposition and wastes no words.

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?

Given the presence of an output schema, the description does not need to explain return structure. It covers required input, optional parameters, limits, use cases, alternatives, billing, and authentication, making it fully actionable for an agent with no prior context.

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?

While schema coverage is 100%, the description goes far beyond the schema: it explains fields as a comma-separated list up to 10 items, clarifies list=true returns an array of repeated records, and confirms text is required. This adds meaningful invocation details beyond the bare parameter descriptions.

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 uses a specific verb and resource: converting unstructured text into schema-enforced JSON via extraction. It clearly distinguishes itself from siblings by noting it is 'the universal parse step' and explicitly routes large jobs to ai-extract-batch.

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?

It specifies when to use this tool ('pages, emails, receipts, logs'), when to add list=true for repeated records, and names the batch alternative for many documents. It also gives concrete constraints like 16K chars and required input text, so an agent can decide to invoke it confidently.

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