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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=true. The description usefully adds that this 'prepares one approval' rather than applying changes directly, which is real behavioral context beyond the annotations, but it omits the confirm/deny flow, permission prerequisites and what happens if the approval is never confirmed.

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?

Single front-loaded sentence with no filler, but it terminates with a dangling comma and reads as an unfinished clause, and the enumerated field list is the only content it carries.

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 mutation tool with a nested changes object, an output schema and a large family of more specific prepare/confirm siblings, the description leaves key gaps: no routing guidance, no mention of the approval/confirm workflow, and a campaign-only scope claim that conflicts with the adset/ad levels the schema permits.

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 40%, so the description must partly compensate. It does enumerate the change categories (status, name, budget, bid, schedule, spend cap, targeting, frequency), which maps onto the changes object, but it adds nothing for level, ids, ad_account_id or connection_context beyond what the schema already states.

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 (prepare) and resource (entity changes) and enumerates the mutable field families, so the agent can tell it is the generic multi-field prepare step rather than the single-field siblings like campaigns_prepare_status_change. However it says '1-10 campaigns' while the schema's level enum allows campaign, adset and ad, which slightly narrows the stated scope.

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?

No when-to-use guidance at all. With many adjacent siblings (campaigns_prepare_status_change, adsets_prepare_budget_change, console_prepare_change, operations_confirm_campaign_status), the description never explains when to prefer this generic tool over a specific one, nor that a prepare must be followed by a confirm step.

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