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

With no annotations, the description carries the full burden and does a decent job: it discloses what is returned (invitations and verdicts), that the data is private, that access requires an API key, and that verdicts can be stale. It also warns that frozen receipt text is untrusted data rather than instructions, a real prompt-injection guard. It stops short of describing pagination or result volume.

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 short sentences, purpose front-loaded, then security caveat, then staleness caveat, then auth requirement. No sentence repeats structured data and none could be dropped without losing a fact.

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?

No output schema exists, and the description partially compensates by naming the two things returned (invitations, verdicts). Auth, trust boundary, and staleness are all covered. Minor gaps remain around result shape and whether invitations include any identifiers the agent would need downstream.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly implies a parameterless full listing of the caller's own reviews.

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 (read/list) and a specific resource (private independent delivery review invitations and verdicts), along with the scope 'your private'. However, it does not name or contrast with the obvious sibling manage_independent_review, so the agent must infer the read-only counterpart relationship.

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?

'Check stale before relying on a verdict' gives a concrete usage condition, which is more than most. But there is no explicit statement of when not to use this tool or which sibling to use for the mutation side (manage_independent_review), leaving usage largely implied.

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