Cancel Unstarted Import

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

The description adds useful behavioral detail beyond annotations: non-processing state restrictions and the fact that it returns the actual state if the job already finished, which prevents false error assumptions. Annotations already clarify it is non-read-only and non-destructive, so this is stronger than baseline, though it does not explain idempotency or permission requirements.

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 cancellation scope, followed by the key restriction and edge-case return behavior. Every sentence earns its place with no 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 mutation tool with no output schema and basic annotations, the description covers state gating and the already-finished case. However, it omits explanation of the two required parameters and does not describe authorization or side effects of cancellation, leaving meaningful gaps.

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 carry parameter meaning. It never explains 'campaign_id' or that 'reference' is a typed object accepting either a job or handoff UUID, leaving the agent to infer the parameter structure entirely from 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?

The description states a specific verb ('Cancel') and resource ('pending handoff or awaiting-upload/queued job'), making clear it is a cancellation tool for unstarted imports. It does not explicitly name sibling tools such as confirm_campaign_creator_import, but the state qualifiers distinguish it well enough.

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?

It clearly states when cancellation is allowed ('pending handoff or awaiting-upload/queued job') and when it is not ('Processing jobs cannot be cancelled'), providing strong usage context. It does not name an alternative action for processing jobs (e.g., check status via get_campaign_creator_import), so it stops short of full alternative routing.

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