backtranslate_eval

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

With no annotations, the description carries the full burden. It discloses the back-translation process, model selection defaults, and return values. However, it does not mention potential failure modes (e.g., model unavailability) or explicitly state read-only behavior, though it is implied.

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-front-loaded with the purpose and process, followed by a structured parameter list. It is slightly verbose but each part adds value; could be tightened slightly without losing clarity.

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 8 parameters (4 required) and an output schema, the description covers the purpose, process, parameters, and return values adequately. No essential details missing for an evaluation tool.

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?

Despite 0% schema description coverage, the description includes a detailed 'Args' section explaining every parameter, including defaults and examples, providing full semantics beyond the schema titles.

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 that the tool evaluates a translation via back-translation and gloss overlap, with a specific verb-resource pairing. It distinguishes from siblings like 'judge' by explaining its unique non-circular metric approach.

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 explains when to use it as a powerful quality metric and provides context for its use, but does not explicitly state when not to use it or mention alternatives beyond implying it differs from other evaluation tools.

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