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

Beyond the annotations, the description discloses concrete behavioral details: downstream steps that never ran are removed and re-created on the next approval, and the tool refuses with REVIEW_DOWNSTREAM_ALREADY_RAN when a later step already ran. This gives the agent accurate expectations about side effects and failure conditions.

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 dense but every sentence adds distinct value: main purpose, applicable contexts, downstream behavior, failure condition, and entry ID source. It is front-loaded with the core action and avoids redundancy with the schema or annotations.

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 mutating tool with no output schema and only two simple parameters, the description provides enough operational detail: what state changes occur, what happens to downstream steps, when it refuses, and where to get the required entry ID. No critical decision information is missing.

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?

With 0% schema description coverage, the description must compensate for parameter meaning. It adds useful guidance for entryId by pointing to campaignstack_get_lead_history, but it does not explain workspaceId or how the two parameters relate to the review context. Partial but not complete compensation.

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 states a specific action: returning an already decided review to the pending queue with its stored draft, and distinguishes this from approval, rejection, editing, and retrying. It also specifies the two applicable node contexts, making the tool's unique role clear among the many review-related siblings.

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 clearly explains when to use the tool: for already decided reviews parked at a review or craft node, and when not to use it: when downstream steps have already executed, with a refusal code. It names the source for entry IDs but does not explicitly route to alternative sibling tools such as approve_review or retry_review.

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