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

The description goes beyond the readOnly annotation by providing behavioral instructions, such as using the 'summary' field as the single source of truth, translating responses, and not echoing raw status values or field names. However, it does not cover potential errors or rate limits, so it's not exhaustive.

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 detailed and well-structured, covering multiple aspects without being excessively verbose. Some redundancy exists (e.g., repeating the instruction to avoid adding details), but overall it is concise enough for its complexity.

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?

The description provides comprehensive context: its relationship with convert_statement, handling of output formats, data modes, and the specific instruction to use original data_mode when passing to evaluate_benchmark. This makes it self-sufficient for proper usage.

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 description explains the nuanced parameters output_format and data_mode in depth, clarifying defaults, formats, and their effects on the response. It does not explicitly explain limit/offset or document_id, but these are standard pagination and identifier parameters that are self-evident from the 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: 'Fetch the full converted data for a previously processed document.' It also distinguishes it from siblings by specifying when to use it (after convert_statement returns a 'processing' status) and when to re-fetch results.

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 when to use the tool: 'Use this after convert_statement returns a 'processing' status, or to re-fetch results.' It also provides detailed guidance on output_format and data_mode options, including their defaults and implications.

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