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

Annotations cover idempotency, read-only=false and non-destructiveness, and the description adds genuinely useful non-annotationed context: the saved artifact is an inactive review draft, no credits are spent, and nothing is published. It does not describe permission requirements or the preconditions for the recipe's 'type' matching.

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, lead sentence front-loads the action, and the negative scope follows immediately. It is efficient, though very terse for a payload this deep.

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 a deeply nested recipe schema with zero property descriptions and no output-schema-related burden, the description should carry more; an agent has no guidance on how to assemble the recipe or the 'type must match' constraint. The safety/usefulness framing is present, but the structural gap is large.

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 object alone contains ~18 undocumented nested fields (mode, horizonDays, runCap, pieceBriefs, attachmentIds, etc.). The description never mentions brandId, recipe, or idempotencyKey and gives no field-level meaning, so it 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?

States a specific action ('Save an inactive review draft') and explicitly what it does not do (generate content, spend credits, publish), which routes the agent away from the generate_*_sample and activate_* siblings. It never states the resource as an 'automation' or names a sibling explicitly, so it stops short of a 5.

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 constraints ('Only written campaign sections; the saved automation type must match this tool') imply when the tool is applicable and pair with the sibling set, but there is no explicit when-to-use vs prepare_campaign / update_campaign_generator_automation / activate_campaign_generator_automation guidance.

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