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

Beyond the annotations (destructive, non-idempotent, open-world), the description discloses the authorization prerequisite, the safe dry-run pattern, the pending state and request_key resumption, and a recovery tool for lost responses. These are exactly the traits an agent cannot get from annotations alone.

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 tightly packed sentences with the action front-loaded and the confirm workflow, pending state, and recovery pointer following in priority order. No 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?

An output schema exists, so return values needn't be described. The description covers the destructive-confirm pattern, the pending/resume edge case, and failure recovery, which is complete for a mutation tool of this complexity.

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 confirm, request_key, and the other parameters are already documented in the schema descriptions. The description reinforces the confirm/request_key workflow but adds no syntax or format detail beyond what the schema already provides, making the 3 baseline correct.

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 ('Submit for App Store review') that is immediately distinguishable from read/update siblings like get_review, update_review, and review_lint. An agent knows exactly what action is being performed.

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?

Explicitly prescribes the sequence: run without confirm first to see the staged result + Apple blockers, then repeat with confirm:true only with authorization. It also names the recovery path (get_store_operation) and the pending-resume condition, leaving no inference required.

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