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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, but the description adds real value beyond them: it discloses the validation ordering (other operation kinds are rejected before anything is reserved or applied) and the concrete external consequence (changes Meta advertising state, may affect spend). It stops short of idempotency or stale-digest behavior.

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?

Two sentences, purpose front-loaded, no filler. The second sentence is dense with three distinct facts (plan source, rejection ordering, external side effect) but each earns its place.

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?

With an output schema present and annotations covering the destructive profile, the description supplies the missing preconditions and side-effect disclosure an agent needs to call this safely. A brief note on digest-mismatch handling would make it complete.

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 coverage is 0%, so the description must carry the parameter burden. It explains the roles of approval_ref (selects the stored plan) and expected_plan_digest (binds the confirmation to an exact plan), but says nothing about connection_context or why the digest is required, so the compensation is only partial.

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 (replace the bid amount of one Meta ad set) plus the required precondition. It is clearly separable from siblings such as operations_confirm_adset_budget and operations_confirm_adset_status without opening any schema.

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?

"After explicit user approval" states the gating condition and "uses only the stored plan selected by approval_ref" tells the agent the plan must already exist. However, it never names the prepare sibling (adsets_prepare_bid_change) that produces that approval, so the entry point into the flow is left to inference.

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