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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does add the pay-per-use pricing detail (0.01 USDC on Base), which is useful context, but it fails to explain what output the agent should expect, whether it accepts images, PDFs, or URLs, or how the table extraction result is returned. This is a significant gap for a tool with no annotation safety or behavior signals.

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 very short and front-loads the main function, with pricing appended in brackets. It avoids verbosity, but it is so sparse that it reads more like a tagline than a functional description, and it does not provide enough earning sentences to guide invocation.

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 large sibling set of OCR and table-related tools, the description is not complete enough for an agent to invoke the tool correctly with confidence. It omits input format expectations, output shape, and any conditions that distinguish this tool from alternatives like vision-tables or ocr-structured-json. The pricing note is helpful but does not compensate for the missing operational 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?

The schema describes the only parameter as 'pipeline input', which is generic and uninformative even though schema description coverage is formally 100%. The tool description adds no detail about what the input should be, so the agent cannot tell whether to pass a URL, file path, or base64-encoded document. Baseline is 3 because the schema technically documents the parameter, but the semantic value is low.

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 that the tool performs OCR specialized for tables, which identifies both the verb (OCR) and the target resource type (tables). It differentiates at least partially from many sibling OCR tools that target invoices, receipts, handwriting, or general documents, though it does not specify what kind of table input is accepted.

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?

The phrase 'specialized for tables' implies the tool should be used when table-like documents are the input, which gives some usage context. However, it does not explicitly state when not to use it or mention alternatives such as ocr-structured-json, vision-tables, or destilar-tables, leaving selection partially to inference.

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