MCP Server Box

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

With no annotations provided, the description carries full burden for behavioral disclosure. It does well by describing key behavioral traits: that it returns a SINGLE metadata instance even with multiple files, uses advanced AI models (Gemini), handles complex layouts and low-quality scans, and combines information from all files. However, it doesn't mention potential limitations like file size constraints, processing time, or error handling, which keeps it from a perfect score.

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 well-structured and appropriately sized. It starts with a clear purpose statement, then details enhanced features, use cases, exclusions, and finally parameter explanations. Every sentence adds value - no fluff or repetition. The information is front-loaded with the most important details first.

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?

For a complex extraction tool with no annotations and no output schema, the description does an excellent job. It explains the tool's behavior, use cases, limitations, and parameters. The main gap is the lack of information about the return format beyond 'dict: The extracted structured data in a json string format' - more detail about the structure of the returned data would be helpful given no output schema exists.

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?

With 0% schema description coverage and 2 parameters, the description adds significant value beyond the bare schema. It explains that 'file_ids' are 'IDs of the files to read' and provides concrete examples of what files might contain. For 'template_key', it gives an example ('insurance_policy_template') and explains it's 'the key of the metadata template to use for the extraction.' This compensates well for the lack of schema descriptions.

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 purpose: 'Extract structured data from one or more files and return a SINGLE metadata instance (Enhanced version).' It specifies the verb ('extract'), resource ('structured data from files'), and distinguishes from siblings by mentioning it's an 'enhanced version' and explicitly contrasting with batch processing. The description differentiates from sibling tools like 'box_ai_extract_structured_using_template_tool' by emphasizing enhanced AI models and multi-file consolidation.

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 explicit guidance on when to use this tool vs alternatives. It states 'Use cases' with examples for single and multiple files, and crucially includes a 'NOT for batch processing' section that explicitly tells when NOT to use it ('If you need to extract metadata from multiple files as separate instances, call this tool once per file in a loop'). This gives clear alternatives and exclusions.

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