extract_text_from_screenshot

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 disclose the OCR function and applicable content types, and mentions the optional 'question' parameter for specific extraction needs. However, it does not mention limitations (e.g., on non-text images or handwriting) or failure modes, leaving gaps in transparency.

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 concise and well-structured, front-loading the main purpose and then presenting a clean argument list. Every sentence adds value with no redundant repetition of schema or annotations.

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 tool's simplicity (two parameters) and the existence of an output schema, the description covers the essential aspects: function, use cases, and parameter details. It could be more complete by explicitly stating limitations (e.g., not suitable for charts or handwriting), but for this complexity level it is sufficiently complete.

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's parameters have no descriptions (coverage 0%), but the 'Args' section in the description thoroughly explains both: image accepts path/URL/base64 URI, and question is optional with an example ('只提取报错堆栈'). This fully compensates for the missing schema descriptions and adds meaningful context beyond raw schema.

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 '对截图进行 OCR,提取其中的文本' (Perform OCR on screenshots, extract text), giving a specific verb and resource. It also lists applicable content types (code, terminal output, documents) and clearly distinguishes itself from sibling tools like image_analysis and diagnose_error_screenshot, which serve different purposes.

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 explicitly states suitable content types ('适用于代码、终端输出、文档、普通文本等'), providing clear context for when to use the tool. However, it does not mention exclusions or alternative tools, so it lacks explicit when-not guidance.

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