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

Annotations declare the mutation profile (readOnlyHint=false, destructiveHint=true), which is consistent with the description's disclosure that re-submitting overwrites/updates the existing review. Beyond that, the description adds workflow-critical behavior the annotations cannot convey: the mandatory draft-and-confirm step, the fact that checkable claims are stamped against network records with evidence chips, and a strict no-embellishment rule for the comment.

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?

Front-loaded with purpose and the structuring instruction, and every sentence carries operational weight (mapping example, confirmation requirement, overwrite semantics, order resolution). It is on the long side with two quoted examples, but none are filler given the ambiguity of natural-language-to-facet conversion.

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 mutation tool with nested params, 100% schema coverage, and no output schema, the description supplies the missing pieces: the confirm-before-send workflow, overwrite-on-resubmit semantics, and that evidence chips are attached server-side. Return values are not explained but an output schema is absent and the key side effect (review creation/update with evidence) is disclosed.

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 100%, so the baseline is 3, but the description adds real interpretive value: it maps natural-language complaints ("cut was sloppy", "arrived 2 days late", "wrong color") onto the quality/timeliness/accuracy facets and illustrates how claims should be derived ("never showed up" -> not_delivered). It does not add much on order_id beyond pointing at list_orders, but the facet/claim mapping guidance exceeds the schema text.

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+resource (record a verified-purchase review of a UFP order) and immediately frames the agent's task: converting free-text feedback into stars and facet scores. This is unambiguous and clearly distinct from sibling tools like get_order_status or reply_to_maker.

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?

Explicitly says when to use it (after the user reports how an order turned out), what to do first (draft and confirm with the user before calling), how to resolve ambiguity (use list_orders to find the order), and what happens on repeat calls (one review per order, resubmission updates). Both alternatives and preconditions are covered.

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