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

Beyond annotations, it discloses 'Costs 1 credit per successful call', which explains the non-read-only billing side effect implied by readOnlyHint=false. It also reveals return fields (confidence score, review_needed flag) and schema-guaranteed output, which are absent from an output schema.

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?

Three compact sentences front-load the core extraction behavior, then cover input mechanism, optional controls, return values, and cost. No filler or redundancy.

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 no output schema, it correctly names return values, and all 7 parameters are covered by the schema. Missing operational details like conflict between url/base64 or file-size limits are minor and don't prevent correct invocation.

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 description coverage is 100%, and parameter docs already describe url, base64, media_type, schema, schema_id, redact, and instructions. The description only summarizes url/base64/schema/instructions without adding new semantics, so baseline 3 is appropriate.

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?

Description uses specific verb 'Extract' with clear resource 'PDF or image' and outcome 'clean, schema-guaranteed JSON', which differentiates from sibling parse_text. It tells agent exactly what tool does.

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 clearly scopes usage to PDF/image inputs and states input methods (url or base64) and optional schema/instructions. It doesn't explicitly say when to choose parse_text or when not to use this tool, but the context is clear.

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