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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered; the description then adds genuinely new behavioral context: media is preserved despite the destructive hint, and there is a runtime precondition tied to in-flight video batches. Missing is what happens to consumed credits and whether a cancelled production can be revived via restore_production.

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 short sentences, zero waste, with the most decision-relevant fact (media retained) front-loaded in the parenthetical and the blocking condition second.

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 single-parameter mutation whose annotations already declare destructiveness and non-idempotency, the description supplies exactly the extra facts an agent needs: what survives the operation and when the call is invalid. Return values are not needed since the caller can re-read via get_production/list_productions.

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 schema itself documents productionId including its origin (list_productions or create_production), so the description need not repeat it. The description adds no meaning about the ID beyond what the schema provides — baseline 3.

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?

Specific verb ("Stops") plus a precisely scoped resource ("a waiting production"), and the parenthetical "media retained" implicitly distinguishes it from sibling remove_production, which presumably deletes. It does not name that sibling outright, so differentiation is inferred rather than stated.

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 a concrete when-not condition ("Not allowed while a video batch may still be running"), which meaningfully steers the agent away from a failing call. It stops short of naming alternatives such as remove_production, restore_production, or retry_production for the cases this tool doesn't cover.

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