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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description still adds useful context: no account needed, what fields each profile carries, the gauntlet stage order, verdicts per mode, and the hosted/core split. It stops short of describing pagination or output shape, but the output schema exists and covers that.

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 sentences, front-loaded with the call-first directive and then progressively detailing return contents and the hosted/core routing. Slightly dense – a couple of the enumerated fields could be trimmed – but nothing is 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 zero-param discovery tool with an output schema and full annotations, this is complete: it says when to call, what comes back, and how the result routes into the two sibling tools that actually run reviews.

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?

Zero parameters, so baseline is 4. Description correctly implies a parameterless enumeration and even states what it feeds into run_review (provider and model ids), which is meaningful context beyond the empty schema.

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?

Specific verb+resource ('list review profiles') and explicitly frames itself as the discovery/first-call tool, distinguishing it from siblings run_review and prepare_review by describing what it returns and how those siblings consume hosted vs core profiles.

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?

Front-loads 'Call first when you do not know which review fits' – an explicit when-to-use rule. Also routes downstream: hosted profiles → run_review, core profiles → prepare_review, which tells the agent what to do after this call.

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