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

Annotations already declare destructiveHint=true and openWorldHint=true; the description goes beyond them by disclosing credit-cap consumption and that previously approved delivery can auto-publish to connected channels. That is meaningful side-effect context, though it stops short of describing what resuming does to in-flight runs or existing schedules.

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 action and followed by the side-effect and scope constraints. Minimal waste, though 'using the saved recipe and credit caps' is slightly vague phrasing for something that matters operationally.

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 the description covers the mutation's scope and side effects. However, for a destructive, idempotent-keyed, revision-guarded call with four undocumented required parameters, the description leaves too much of the invocation contract unstated.

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% across all four required parameters, so the description carries the full burden and largely fails: brandId, automationId, revision, and idempotencyKey are never explained. 'Saved recipe' loosely gestures at automationId, but the optimistic-concurrency 'revision' requirement and the idempotency key contract are left entirely opaque.

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 and resource (resume recurring generation of a saved automation recipe), and the final sentence carves out scope: 'Only written social posts; the saved automation type must match this tool.' That differentiates it from the many sibling resume_* automation tools, though it doesn't name them explicitly.

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?

Gives a real precondition for use: the saved automation type must match this tool, and delivery only publishes if previously approved. It does not name alternatives such as pause_automation or the activate_* siblings, so the routing guidance 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.