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

Annotations already flag destructiveHint=true, but the description adds substantial context beyond that: lineage preservation, transfer of prerequisites and downstream dependents, cancellation with supersession provenance, and the critical guarantee that old artifacts remain in audit history while "nothing is marked delivered." This materially refines what the destructive hint means and prevents false assumptions about history loss.

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 sentences with no filler: purpose, mechanism, and preservation guarantee each earn their place. The final sentence is high-value because it clarifies what a destructive operation does NOT do (mark delivered, erase history), which an agent would otherwise have to guess.

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 complex destructive mutation with six required parameters, the description covers the core contract well: trigger condition, artifacts created, relationships transferred, and preserved state. The output schema covers return values, so that omission is acceptable. A brief note on prerequisites (e.g., what happens if the task is not actually blocked) would push it to complete.

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 description coverage is 0%, so the description carries the burden for parameter meaning. It implicitly maps most parameters — task_id is the blocked task being replaced, title/body_md/acceptance_criteria describe the new task, project_id anchors the roadmap item — but does not explicitly tie parameters to the described behavior. decision_md's role is especially left to inference.

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 opens with a specific verb+resource+qualifier: "Replace an unretryable blocked task without losing its lineage." It then details the exact mechanics — creating a fresh planned task, transferring prerequisites and dependents, and cancelling the stale task with supersession provenance — which clearly differentiates it from siblings like retry_blocked_task and close_task.

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 qualifier "unretryable blocked task" in the first sentence gives clear context for when to use this tool, and contrasts naturally with the sibling retry_blocked_task for retryable cases. However, it never explicitly names the alternative or states a when-not-to-use condition, leaving the routing slightly implicit.

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