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

Annotations already mark this as read-only/idempotent/non-destructive; the description adds concrete behavioral context: guaranteed-valid JSON via structured outputs, 16K char limit, list=true array behavior, and pricing/auth requirements (x-credit-token header, free tier). 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?

Dense and front-loaded: the core purpose and usage appear first, followed by limits, alternative, and pricing/auth. All sentences carry operational information an agent needs; 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?

Covers input requirements, field limits, list behavior, input size cap, alternative for batch, pricing, auth, and free tier. With an output schema present, return structure is already specified; nothing essential 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?

Schema already documents text, fields, and list with 100% coverage. Description adds meaningful semantics: fields are comma-separated and capped at 10, list=true extracts every repeated record as an array, and text is required input.

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+resource: transforms unstructured text into schema-enforced JSON with user-specified fields. It explicitly differentiates itself from ai_extract_batch ('Many documents?') and clarifies it is not crypto-specific, so an agent can distinguish it from sibling parsing/summarization tools.

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 when-to-use context: use for one-call extraction from pages, emails, receipts, logs, and names ai-extract-batch as the alternative for many documents. It does not explicitly exclude summarization/translation siblings, so it falls short of full when-not guidance.

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