Kill Transaction

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 structured data. The description adds genuinely non-obvious consequences beyond that: the in-flight work stops part way and is not undone, and the originating user receives an error — exactly the impact information an agent needs before invoking a destructive action.

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 short sentences, front-loaded with the action and its platform equivalent, followed by consequences and then preconditions. No filler and no repetition of name or title.

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, open-world mutation tool, the definition covers what it does, the irreversibility, the side effect on the initiating user, and the authorization precondition. With annotations carrying safety hints and a fully documented schema, nothing an agent needs before calling 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 transaction_id, confirm, and instance are already documented, including the confirmation sys_id pattern. The description only restates that the transaction comes from list_transactions and says nothing about the confirm safeguard or instance fallback, so it adds little 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?

Names a specific verb ('cancel') and a precisely scoped resource ('one active transaction'), and ties it to the platform's 'Kill action on Active Transactions'. It is clearly separable from the sibling list_transactions, which it explicitly references as the discovery step rather than a competing option.

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 an explicit gating condition ('Only when the user asked'), a required provenance for the target ('for a transaction found with list_transactions'), and a hard exclusion ('never one of your own requests'). This is a complete when/when-not/alternative instruction set with no inference required.

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