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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds behavioral facts those annotations cannot convey: paying accounts get draft credits back, the batch matches what the user saw in list_pending_drafts, and the action cannot be undone. This is exactly the extra context the safety profile alone lacks.

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?

Four short sentences, front-loaded with the destructive intent, then the credit-refund consequence, then the sibling alternative, then the batchId source. Every clause carries distinct operational information with no filler.

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?

No output schema exists and the description needn't describe returns; for a 2-required-param destructive tool it covers scope, irreversibility, credit refund, alternative tool, and parameter sourcing. Nothing an agent needs to call it safely 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?

Schema description coverage is 100%, so both parameters are already documented and the baseline is 3. The description restates the batchId provenance from list_pending_drafts but adds no new syntax, format, or constraint beyond the schema.

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 (discard) and resource (every draft still pending in the batch) with the scope spelled out as 'every ... so none of them go out'. It explicitly contrasts with the sibling discard_draft, so an agent can differentiate without opening either 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?

Names the alternative tool (discard_draft) and the condition that selects it ('to drop just some'), and directs the agent to list_pending_drafts as the source of batchId. Both when-to-use and the alternative route are explicit.

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