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

Annotations only declare the safety envelope (readOnly=false, destructive=false, idempotent=false). The description adds behavior beyond that: retry 'may spend a fresh model generation' (cost/quota implication) and reopen 'validates downstream safety'. Missing detail on reversibility and any permission requirements keeps it from a 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?

Two tight sentences with zero filler; the resource and mode enumeration are front-loaded before the cost caveat.

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 explained, and the cost note covers the mutation risk. However, for a confirmed-required mutation with an undefined entryId and no guidance on when to prefer recovery over decide_review, the description leaves meaningful gaps.

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 50%: confirmed and workspaceId are documented inline, but entryId and mode are not. The description compensates partly by spelling out the three valid mode values, yet says nothing about what entryId expects (an id vs a review object). Baseline 3 for partial coverage.

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 ('Recover one review') and enumerates the three modes it supports, which makes it clearly distinct from read siblings like get_reviews or decide_review. It stops short of naming the closest alternative (decide_review) explicitly, so differentiation is inferred rather than stated.

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 mode list implies the situations (retry a failed generation, restore a superseded draft, reopen a decision), but there is no explicit when-to-use vs when-not-to-use guidance or reference to the sibling decide_review, which handles the non-recovery path.

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