MCP Server Box

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 effectively describes key behaviors: it returns a single response (not batch), analyzes all files together for multiple inputs, provides unstructured results, and mentions flexibility vs. consistency trade-offs. However, it doesn't cover potential limitations like rate limits, authentication needs, or error conditions.

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 front-loads the core purpose, then provides usage guidelines, use cases, and exclusions. While slightly verbose, every section adds value. The 'Args' and 'Returns' sections are redundant with the schema but help readability.

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 3-parameter tool with no annotations and no output schema, the description provides strong context: clear purpose, usage guidelines, parameter explanations, and behavioral traits. It adequately compensates for the lack of structured metadata. However, it doesn't detail the response format beyond 'dict' or potential error cases, leaving some gaps.

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, the description must compensate, which it does excellently. It explains that 'file_ids' is 'a list of file IDs to extract information from' with an example, clarifies 'prompt' as 'the fields to extract' (though this could be more precise), and notes 'ai_agent_id' is optional with default behavior. This adds substantial meaning beyond the bare 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 clearly states the tool's purpose: 'Extract or analyze information from one or more files using a natural language prompt and return a SINGLE response.' It specifies the verb ('extract or analyze'), resource ('files'), and distinguishes from siblings by contrasting with 'structured extraction tools' and mentioning sibling tools like box_ai_extract_structured_using_fields_tool.

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: 'Use structured extraction tools... when you need consistent, machine-readable output' and 'NOT for batch processing... call this tool once per file in a loop.' It also lists specific use cases and contrasts with structured tools, giving clear context for selection.

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