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

Annotations only say readOnly=false, destructive=false, openWorld=false; the description adds far more: writes land as unsaved changes the user reviews and saves in Xodia, new item translations default to draft, shared fields (dates, prices, images, references) are refused, and languages beyond the plan allowance are refused with plan_limit. Per-entry outcomes (set, removed, unchanged, failed with why) are disclosed so the agent knows partial success is possible.

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?

It is one dense paragraph but well ordered: purpose, then payload rules, then formatting/quality rules, then the opt-in policy. Slight cost for length and for restating the numbered-tag rule that the schema already carries, but nearly every clause carries operational information rather than 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?

For a 6-parameter write tool with no output schema, the description covers everything an agent needs: what gets written and where, the unsaved/draft state, two refusal conditions, per-entry results and the retry loop, plus translation style and placeholder-safety constraints. No significant gap remains that would cause a mis-call.

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 description coverage is 100%, so the baseline is 3; the description earns above that by defining the cross-parameter routing ('entries: page texts ... never put CMS item text here') and the back-reference requirement that `text` be exactly what get_translations returned. The tag/placeholder preservation rule is repeated from the schema but framed as a translation-quality constraint rather than a format note.

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?

Opens with a specific verb and resource ('Writes translations for one language') and immediately distinguishes the two payloads it accepts: page texts via `entries` versus CMS item text via `collection` + `items`. It also names the sibling that produces the input text ('as get_translations gave it'), so an agent can tell it apart from get_translations and update_item without opening a schema.

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?

Gives an explicit when-to-use rule ('Translate only when the user asks for it... never on your own while building or editing') and an explicit when-not-to-route-here rule ('never put CMS item text here, it is translated with collection and items'). It also states the retry protocol ('fix and send only the failed ones again'), which is exactly the guidance an agent needs after a partial failure.

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