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

Annotations declare a mutation (readOnlyHint=false), non-destructive, idempotent operation. The description adds real value beyond that: it states the draft is saved inactive, that no content is generated, no credits are spent, and nothing is published. This clarifies the operational footprint well, though it doesn't describe auth requirements or caps.

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 primary action and then the negative constraints. Nothing is wasted and the essential scoping is up front.

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?

Output schema handles return values and annotations cover the safety profile, so those gaps are filled elsewhere. But for a tool whose recipe argument is this complex with zero field documentation, the description does not provide enough to construct the call correctly.

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 recipe parameter is a deeply nested object with dozens of undocumented fields. The description says only "written carousel sections" and offers no guidance on brandId, the recipe shape, or idempotencyKey, so it fails to compensate for the schema 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 clear verb+resource: "Save an inactive review draft," and clarifies scope by noting it only handles written carousel sections and that the saved automation type must match this tool. This distinguishes it from activate_* and update_* siblings, though it never names the carousel creator automation explicitly in the opening sentence.

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 negative constraints (does not generate content, spend credits, or publish) imply this is the pre-activation draft-saving step, and "the saved automation type must match this tool" gives a routing constraint. However, no sibling is named and no explicit when-to-use vs when-to-activate guidance is given.

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