run_access_review

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

Without annotations, the description carries the full burden. It reveals that the tool performs a review and returns a markdown report plus recommendations, with the recommendation types explicitly listed, implying it does not directly execute changes. It does not mention permissions or rate limits, but the read-only nature is implied by the review-and-recommendation flow.

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?

The description is a single, well-structured sentence that front-loads the action and includes specific output details and recommendation types without any redundant content.

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?

Given zero parameters and no output schema, the description provides sufficient context: it states the process, the scope, and the output format. The enumerated recommendation types provide valuable detail for an agent to handle the response, making the description complete for this tool's simplicity.

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 has zero parameters, so the schema is trivial. The description adds meaningful context by specifying the scope ('for the current tenant'), which clarifies what the operation applies to, though it does not need to explain any inputs.

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?

The description clearly states the tool triggers an on-demand AI-driven access review for the current tenant, with a specific verb and scope. It also enumerates the review targets (users, service accounts, anomalies) and outputs, distinguishing it from sibling tools like query_session_anomalies or list_tenant_users, which focus on narrower tasks.

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 description implies usage by describing it as an on-demand review for the current tenant, suggesting it is appropriate for comprehensive access evaluations. However, it does not explicitly compare to sibling tools or state when not to use it, leaving some ambiguity about alternative tools for specific queries.

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