Pause or activate many entities

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

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) by disclosing the real-world consequence that 'ACTIVE starts spending as soon as the parents are active too', the write-guard escalation via confirm='APPLY', and that prior statuses are retained in the audit log. These are precisely the side effects and recovery details an agent needs before firing a bulk mutation.

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 lines, zero filler: purpose and scope first, then per-parameter semantics, then the escalation rule. The 'with progress' lead-in is slightly terse but signals long-running behavior that the output schema then details.

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 bulk mutation with 5 parameters and an output schema, this is nearly complete: it covers spending consequences, the confirm guard, audit retention, and the archive alternative, so return values needn't be restated. The gap is the ids/ad_account_id relationship and partial-failure behavior, which an agent must still infer.

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 the description carries the burden; it enumerates entity values ('campaigns', 'ad_groups', 'ads'), status values ('PAUSED'/'ACTIVE'), and explains confirm's threshold semantics even though the schema shows no enum for it. It leaves ids and ad_account_id unexplained — notably whether ad_account_id is required to scope the ids or whether ids are globally unique.

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 pair plus resource and scope: 'Pause or activate many campaigns, ad groups or ads at once, with progress.' It also explicitly draws the boundary against the archive siblings ('to archive, use the matching archive tool'), so an agent can separate this from pinterest_ads_archive_campaigns/ad_groups/ads without inspecting schemas.

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 clear selection context: use this for status changes, use the matching archive tool for archiving, and use this for bulk ('many ... at once'). It also states the guard condition (more than PINTEREST_ADS_BULK_THRESHOLD items need confirm='APPLY'). It does not address when to prefer this over update_campaigns/ad_groups/ads for the same field, which is the remaining ambiguity.

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