Card Quarantine

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

With no annotations at all, the description carries the full disclosure burden, and it does convey the key side effect: cards are removed from the active batch and moved into a quarantine record, letting the rest proceed under PARTIAL_PASS. It does not say whether quarantine is reversible, whether the active batch is mutated in place, or what permissions are required for a destructive-feeling operation.

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?

The behavioral purpose is front-loaded in the first sentence and the parameter notes follow compactly. There is little waste, though the parameter notes read as a terse appendix rather than integrated guidance.

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?

An output schema exists, so return values need not be explained, and the core mutation is described. However, for an unannotated mutation tool with three parameters, the definition leaves gaps: reason is undocumented and the reversibility/state effects of quarantine are unstated.

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, and it partially does: drafts_json is identified as a list of CardDraft objects and failed_indices is clarified as 0-based indices of cards to isolate, which is meaningful beyond the bare schema. The third parameter, reason, gets no explanation despite having a non-obvious default value.

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 outcome: 'Partition invalid cards out of the active batch into a quarantine record', which tells an agent exactly what the tool does to which resource. It also names the downstream consequence (G3 export under PARTIAL_PASS). It stops short of differentiating itself from siblings like batch_auto_fix or card_patch_apply, which also touch invalid cards.

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 phrase 'Allows the remaining valid cards to advance through G3 export under PARTIAL_PASS' implies the situation in which this tool is appropriate, namely when a batch has irreparable cards but should still ship partially. It never states when NOT to use it or points to the repair alternatives (batch_auto_fix, card_patch_apply) that would be the correct choice if the cards are fixable.

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