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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine behavior beyond that: the returned value is an *effective* preference set produced by merging per-repo overrides over global defaults, which tells the agent the result is computed, not a raw stored record.

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 short sentences, front-loaded with the core purpose, then the return semantics, then the invocation rule. Nothing is redundant or padded.

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 two-parameter, read-only tool with no output schema, the description covers purpose, return semantics (effective merged preferences) and the optional-parameter behavior. An agent has everything it needs to call it correctly and interpret the result.

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 both parameters are already documented, and the schema itself states 'Omit to get global defaults only'. The description's repository_id note largely restates that; the one added nuance is that supplying it yields merged overrides rather than just the repo row. Baseline 3 is appropriate when the schema carries the load.

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 and resource ('Get the user's AI code-review preferences') and immediately clarifies the resource with the parenthetical 'which categories to check, which to skip'. It is clearly distinct from the write-side sibling set_review_preferences by virtue of its read framing, though it never names that sibling explicitly.

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?

'Call without repository_id for global defaults' gives one concrete invocation rule, which is more than most definitions offer. However, there is no guidance on when to prefer this over set_review_preferences or how preferences relate to the ai_review workflow, so usage is implied rather than fully framed.

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