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

Annotations declare write (readOnlyHint=false), idempotent, and non-destructive, and the description reinforces this by stating it does not generate content, spend credits, or publish. The credit-spend disclaimer is genuinely useful behavioral context beyond the annotations. It does not, however, describe permissions or what happens to a previously saved draft.

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 and the type-matching constraint. No wasted words. It is efficient, though slightly telegraphic at the cost of completeness.

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 no explanation, and annotations cover the safety profile. But given the complex nested recipe object and zero schema descriptions, the definition leaves the agent under-informed about how to construct valid input. Adequate but with clear gaps for a tool of this complexity.

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 the tool takes a deeply nested 'recipe' object with dozens of fields (mode, caps, weekdays, configuration, etc.) that the description never touches. The only hint is the 'automation type must match this tool' constraint on the recipe. For a 3-param tool with a rich nested schema, the description fails to 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?

The description has a specific verb ('Save') and resource ('inactive review draft') and scopes the artifact to 'social post artwork', which distinguishes it from the many prepare_* siblings. The clause 'the saved automation type must match this tool' clarifies the family boundary. It stops short of fully spelling out that it creates a reusable automation definition for later activation.

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 implies usage by framing the result as an 'inactive review draft' that does not generate, spend credits, or publish – a natural pre-activation step. However, it never names sibling alternatives (activate_social_post_creator_automation, update_social_post_creator_automation) or states when to pick this over them. Usage is implied rather than explicit.

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