ocr_table_vision

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

With no annotations, the description carries the full burden. It discloses key behavioral traits: backend, platform requirement, on-device inference, and output format. It does not mention error handling or side effects, but for a read-only OCR tool these are unlikely to be significant.

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 extremely concise and well-structured: a one-sentence action statement followed by a compact backend/purpose note. Every sentence adds value with no filler or repetition.

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?

While the description provides good operational context (backend, platform, language support), it omits explanations for parameters and does not cover usage modes or failure scenarios. Without an output schema or annotations, these gaps make the tool harder to invoke correctly.

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 has 0% description coverage and the description does not explain any of the parameters (path, lang, mode) at all. The agent must infer their meaning solely from names, which is insufficient given the ambiguous 'mode' and 'lang' parameters.

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 clearly states the tool's function: 'Extract tables from an image.' It specifies the output format ('Returns structured CSV/JSON') and identifies the backend ('Apple Vision OCR'), which distinguishes it from sibling paddle and other OCR variants.

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 description provides useful context: 'Best for CJK + major European languages,' 'macOS 10.15+,' and 'Zero install on macOS,' implying when it is preferred. However, it does not explicitly mention alternatives or state when not to use this tool compared to paddle variants.

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