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

The description goes beyond the annotations by disclosing the two-phase approval workflow, the return values (approval_ref, plan_digest), and that 'This call does not change delivery.' The annotations declare readOnlyHint=false and destructiveHint=false, and the description is consistent with that. It doesn't mention auth/permission requirements for the Meta account read.

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 compact sentences, front-loaded with the core purpose, then the approval/confirm flow, then the preferred alternative. Every sentence carries operational meaning with no filler.

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 two-phase mutation with an output schema present, the description fully explains the workflow and point-of-no-return. The main gap is parameter semantics (0% schema coverage) for a required adset_id/bid_amount/ad_account_id triple. It correctly relies on the output schema for return-value structure.

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%, so all four parameters are undocumented anywhere. The description mentions none of adset_id, ad_account_id, bid_amount, or the connection_context pattern, leaving the agent to infer that 'one ad set' maps to adset_id and bid-amount sizing to bid_amount. This is insufficient compensation for a 0% coverage schema.

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?

The description opens with a specific verb+resource+scope: 'Prepare one ad set bid-amount change: read current Meta settings ... and save an approval draft.' An agent can distinguish it from adsets_prepare_budget_change and adsets_prepare_status_change by the operation type (bid amount) and from operations_confirm_adset_bid by the prepare/apply split.

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?

It explicitly states 'apply only after approval with operations_confirm_adset_bid' and 'Prefer entities_prepare_update for new work', giving both the confirm step and an alternative tool. It lacks a clear when-not condition beyond the entities_prepare_update pointer.

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