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

Annotations already declare non-read-only, non-idempotent, non-destructive, open-world. The description adds real behavioral value beyond that: it performs a state transition to pending_review on the same decision, and clarifies that hatchId is derived rather than supplied. It does not mention timeout/session semantics or what the call returns, but the safety profile is adequately covered.

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?

Two sentences, zero filler, with the precondition front-loaded ahead of the effect and the parameter hint. Every clause carries information.

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?

Covers the workflow position, state change, and required parameter for a 7-param, no-output-schema tool. Optional params like sessionToken and timeoutSeconds are left to the schema, which is acceptable but leaves a small gap for a state-mutating call.

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 only 57%, but the description compensates by stating that only decisionId is required and that hatchId is read from the decision, resolving the ambiguity between hatchId and its tenantId alias. It says nothing about sessionToken, title, agentOutput, or timeoutSeconds.

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 (reopen) on a specific resource (the decision) and names the resulting state (pending_review), which distinguishes it from poll_decision and await_decision. An agent can tell what this does without opening the schema.

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?

Gives the exact trigger condition (poll_decision returns changes_requested) and the required preceding action (regenerate), plus the follow-on outcome (next human round). This is explicit when-to-use routing, not inference.

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