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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds the meaningful detail that nothing is applied, which tells the agent the blast radius is limited to the pending batch. It doesn't say whether a discarded batch can be recovered or re-proposed, which is the remaining gap.

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 waste, and the effect ("none of them is applied") is front-loaded before the usage guidance. Every sentence earns its place.

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 one-parameter tool whose annotations already carry the destructive/idempotent profile, the description covers both what happens and when to reach for it. The only omission is what the agent should do afterwards or whether the batch is recoverable.

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% and the single batchId parameter is fully documented, including that it comes from the last propose call. The description adds nothing about the parameter, so baseline 3 applies.

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 and resource ("Discards a pending batch of proposed changes") with the outcome spelled out ("none of them is applied"). This clearly separates it from patroltech_proposals_confirm, though it never names that sibling explicitly.

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 clear positive triggers: when the user declines the proposed changes or wants to start over. It stops short of naming patroltech_proposals_confirm as the opposing path, so the routing is implied rather than explicit.

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