Evaluate Translation Quality

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

The description adds valuable behavioral context beyond annotations. While annotations indicate read-only, non-destructive, and idempotent operations, the description details what the tool provides: quality scores, error spans with severity levels, and human-readable summaries. It also mentions optional reference comparison and output format choices, which are not covered by annotations.

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 with clear sections: purpose statement, what it provides, parameters, return format, and examples. It's appropriately sized for a tool with 7 parameters. The front-loaded purpose statement is effective, though the parameter listing could be more concise given the comprehensive schema coverage.

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 complexity (7 parameters, annotations, output schema), the description is complete. It explains the tool's purpose, what it returns, provides parameter context, includes usage examples, and references the output schema. The combination of description, annotations, and structured data provides comprehensive information for an agent to use this tool 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?

With 100% schema description coverage, the schema already documents all parameters thoroughly. The description lists parameters in the 'Args' section but adds minimal semantic value beyond what's in the schema. It does clarify that 'reference' is optional and provides context for language codes, but most parameter details are redundant with 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: 'Evaluate the quality of a translation using xCOMET model.' It specifies the verb (evaluate), resource (translation quality), and method (xCOMET model). It distinguishes from siblings by focusing on comprehensive evaluation rather than batch processing or error detection alone.

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 clear context through examples: 'Evaluate EN→JA translation quality,' 'Check if MT output needs post-editing,' and 'Compare translation against reference.' However, it doesn't explicitly state when to use this tool versus its siblings (xcomet_batch_evaluate, xcomet_detect_errors), leaving some ambiguity about tool selection.

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