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

Annotations declare destructiveHint=true and idempotentHint=true, and the description aligns with and enriches these by explaining the cancellation, lineage transfer, supersession provenance, and audit preservation. It also explicitly states that nothing is marked delivered, giving the agent a precise behavioral model beyond the annotations.

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 tight sentences: the first delivers the core purpose and scope, the second details behavioral consequences. Every clause contributes meaningful operational information with no filler or redundancy.

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 destructive, non-read-only tool with six required parameters and no schema property descriptions, the description provides strong lifecycle context: what gets created, what gets cancelled, what is preserved, and what is not delivered. It falls slightly short on per-parameter expectations and on explicit guidance about how to identify an 'unretryable' task, but the overall invocation context is well covered.

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 must compensate for documenting what parameters like project_id, task_id, decision_md, and acceptance_criteria mean. It does not name or explain individual parameters, and while line good context, it leaves meaning to parameter-name inference rather than explicit description.

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 and resource: 'Replace an unretryable blocked task without losing its lineage.' It clearly states the operation's intent and its unique scope, distinguishing it from sibling tools like retry_blocked_task, close_task, and cancel_roadmap_item.

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 explicitly scopes usage to 'unretryable blocked task,' which tells the agent when this tool is appropriate and implicitly distinguishes it from retry_blocked_task. It does not explicitly name alternatives or state when-not-to-use conditions, but the context is clear enough.

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