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

Annotations already declare readOnly, openWorld, non-idempotent, and non-destructive behavior. The description adds valuable context annotations don't cover: per-call pricing, the x402/USDC payment mechanism, and that failed calls are not charged. It stops short of describing return shape or latency, though the latter is minor.

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?

Two tight sentences, front-loaded with the core action and scope, with pricing as the secondary clause. No wasted words.

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 three-parameter tool with no output schema, the description covers limits, model, cost, payment, and failure billing, which are the main non-obvious facts. It leaves output format and source-language handling implicit, but those are either obvious or covered by the schema.

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?

Schema coverage is 67%; the description adds the 5,000-character text limit and the 100-language scope for language parameters, which the schema only partially conveys. It does not explain source-language inference behavior, but adds real meaning beyond 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?

States a specific verb and resource (translate text), names the model (M2M100 1.2B), and gives scope (100 languages, 5,000 character limit). This clearly distinguishes it from siblings like summarize and embed_text.

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 purpose implies when to use it, but there is no explicit guidance on when to choose it versus alternatives such as summarize or embed_text, and no stated prerequisites beyond the cost line. Usage is inferred rather than instructed.

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