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

Annotations already flag destructiveHint=true, idempotentHint=false and openWorldHint=true, but the description adds genuinely new behavioral facts: completed assets are reused rather than regenerated, and the call 'may submit new generation' — a cost/side-effect warning the annotations cannot express. It still doesn't say what happens on a non-failed production or whether credits are consumed, keeping it below 5.

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 with no filler, and the highest-value fact (which steps can be resumed, and that completed assets are reused) is front-loaded before the cost warning.

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 with no output schema, the description supplies the essentials: applicable step types, asset reuse, and the possibility of new generation. Gaps remain around failure modes (wrong state, insufficient credits) and whether the response identifies the newly resumed work, which matters given destructiveHint=true.

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% and the single productionId parameter is documented with its UUID pattern and a pointer to list_productions/create_production, so the schema carries the parameter burden. The description adds no format, sourcing, or validation detail beyond it; baseline 3 applies for a one-parameter tool.

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 action (resuming a failed step) and enumerates the step types it applies to (import, images, videos), which is more than the name alone conveys. It does not, however, distinguish itself from near-siblings like restore_production, wait_for_production, or complete_production, so an agent cannot route between them on this text alone.

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 'resuming a failed step' implies the precondition (the production must have failed), and 'explicitly authorizes' hints this is a consent/cost gate the caller must opt into. But there is no explicit when-to-use/when-not guidance and no named alternative for cases like a production that is still running (wait_for_production) or one that was trashed (restore_production).

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