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

Beyond the annotations it discloses three things an agent can't infer: the call consumes the org AI token budget, it obeys a privacy setting and fails with the specific error 'translation_disabled', and it is side-effect free ('only returns text — it never sends anything'). That last point is especially valuable given readOnlyHint=false, which would otherwise suggest a mutating operation.

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?

Three tight sentences, front-loaded with purpose, then cost/privacy behavior, then the no-send guarantee. Every clause carries information an agent needs; nothing is repetitive or filler.

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?

With an output schema present, return values needn't be described, and the behavioral essentials (cost, privacy gate, error code, non-mutation) are covered. Minor gaps remain around input length limits and what happens on unsupported language codes, though maxLength is in 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%: target_language and source_language already document accepted formats and auto-detection in the schema itself. The description adds no language-code or length guidance beyond that, so the schema remains the primary source of parameter meaning.

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 opens with a specific verb and resource ('Translates text') and pins down the backing mechanism ('the org's configured translation providers'). It also gives the conversational triggers ('translate X', 'say this in Hebrew') that route an agent here, and no sibling tool covers translation, so the role is unambiguous.

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 quoted example requests make clear what user phrasings should invoke this tool. It stops short of naming when NOT to use it or an alternative (e.g. drafting a reply in another language vs. translating), so it gives context but no exclusions.

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