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

Goes well beyond the annotations: it discloses automatic credit consumption with a defined failure mode (insufficient credits leave the campaign unscheduled), pre-flight rechecks of facts/revisions/provider validation, approval-grant vs mandatory-review semantics, and a specific success-reporting rule ('report success only from returned post statuses'). This is exactly the kind of operational nuance an agent cannot derive from readOnlyHint/destructiveHint/idempotentHint.

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?

The core action and its gating condition are front-loaded, and most sentences are dense with unique information (credits, review, no immediate publish). Some clauses read as clipped fragments ('Rechecks facts, revisions and provider validation.'), which costs a little readability but 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?

For a mutable, open-world, credit-consuming operation with an output schema, the description covers safety, side effects, approval flow and success-reporting semantics, so an agent can call it responsibly. The remaining gap is parameter explanation, which the schema does not backfill.

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 four required parameters, so the description bears the full burden, yet it only conveys meaning for the snapshot concept ('this exact current snapshot'). brandId, campaignId and idempotencyKey get no elaboration, and the idempotency contract implied by idempotentHint is never tied to the parameter.

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?

Names a specific verb and object (schedule the campaign's current snapshot at its reviewed future times), which is clearly separable from siblings like schedule_post, approve_campaign and prepare_campaign. It stops short of naming an alternative or contrast, so it is clear but not fully self-differentiating.

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 usage condition ('only when the user requests scheduling') and states the authorization rule (owners with an approval grant can approve-and-schedule; mandatory member review remains). It provides when-to-use context but never names a sibling tool or exclusion, leaving the alternative-selection decision mostly inferred.

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