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

Annotations cover the safety profile (destructive, idempotent, openWorld), so the bar is lower. The description adds real context beyond them: credit consumption via 'credit caps' and that previously approved automatic delivery can publish to connected channels — meaningful for a destructive, outward-facing mutation.

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 core action. Some phrasing ('the saved automation type must match this tool') is slightly cryptic, but there is little waste.

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?

An output schema exists so return values need not be explained, and annotations carry the safety profile. However, for a destructive 4-param mutation with zero schema coverage, the omission of parameter meaning (especially revision and idempotencyKey) leaves it only minimally complete.

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% and all four required params (brandId, automationId, revision, idempotencyKey) are undocumented. The description vaguely references 'the saved recipe' and matching automation type but never explains revision or the idempotency key, so it does not compensate for the coverage gap.

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+resource: activate recurring generation from a saved recipe. The clause 'Only banner artwork; the saved automation type must match this tool' implicitly distinguishes it from the ~20 sibling activate_* tools for other artwork types, though it never names a specific sibling.

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?

Usage is implied by 'the saved automation type must match this tool' — use it for banner-generator automations. But there is no explicit when-to-use/when-not guidance, and no differentiation from resume_*, pause_*, or prepare_banner_generator_automation.

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