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

Annotations already declare readOnlyHint/openWorldHint=false, so safety is covered; the description goes further by disclosing data minimization (no source documents, personal fields, or free-text excerpts), the epistemic limits ('does not prove fraud, authenticity, intent, identity or AI generation'), and a cost trait ('No new credit is spent'). Error or failure behavior is still unstated, so not a full 5.

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?

Four compact sentences, front-loaded with what is returned before the caveats and cost note. One could argue the disclaimers are dense, but each conveys a distinct constraint 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?

An output schema exists, so return values need not be re-explained, yet the description helpfully names the categorical fields anyway. Combined with the cost, privacy, and non-proof caveats, an agent has enough to call this correctly; only the meaning of the ID format is thinly covered.

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 0% and the single review_id parameter carries only a regex pattern with no prose. The description adds that the ID must denote 'one recoverable review from the connected purchase', which clarifies ownership/eligibility but not the expected ID form or what to do when a non-recoverable ID is passed.

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 (retrieve) plus the resource and even enumerates the payload: categorical status, priority, confidence, and fraud/AI indicator counts for one review. The scope phrase 'for one recoverable review from the connected purchase' separates it in spirit from list_recent_reviews, but no sibling is named explicitly, keeping it short of a 5.

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 line 'Provides signals for human follow-up' implies the use case but never states when to pick this over list_recent_reviews or get_connected_purchase, nor any prerequisite for obtaining a valid review_id. Usage is inferable, not prescribed.

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