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

Adds valuable side-effect context beyond annotations: resumption consumes credit caps and can publish to connected channels if previously approved. Annotations already declare destructiveness, idempotency, and open-world behavior, so this is solid, though auth and exact destructive scope are not explained.

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 with the core purpose front-loaded. Each sentence adds useful scope or side-effect information, though the final constraint sentence is slightly terse and could be integrated more cleanly.

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?

Given rich annotations and an output schema, the description need not explain return values, and it covers the main action and side effect. However, it omits parameter semantics for all four required inputs and does not clarify when to choose resume over sibling activate/prepare tools.

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?

With 0% schema description coverage and four required parameters, the description must carry parameter meaning, but it only implicitly references the saved automation/recipe. It does not mention brandId, revision, or idempotencyKey, leaving required inputs largely undocumented.

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 (resume) and resource (recurring generation using the saved recipe and credit caps), and constrains the scope to banner artwork. It distinguishes itself from other resume_* automation tools by requiring the saved automation type to match, though it does not explicitly contrast resume vs. activate or prepare.

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?

Implies usage when a saved banner-generator recipe exists and its type matches, and notes that approved automatic delivery may publish to channels. However, it gives no explicit when-to-use alternatives versus activate_banner_generator_automation, prepare_banner_generator_automation, or update_banner_generator_automation.

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