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

Annotations already mark the tool destructive, and the description goes beyond this by specifying 'Permanently delete' and 'Irreversible', which is meaningful because destructive could otherwise include soft-deletes. It also discloses batched execution via campaign_ids, a behavioral trait not present in the annotations, but it does not mention auth requirements or side effects on associated ads/ad sets.

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 description is two crisp sentences with the key action front-loaded. 'Irreversible' and the bulk-support line add essential information without padding or repetition of the tool name.

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 three-parameter destructive mutation tool with no output schema, this description is too thin: auth_account is unexplained, batch-mode semantics conflict with the required campaign_id in the schema, and there is no statement of what happens to sub-objects. It provides a warning but not enough to invoke confidently in all supported modes.

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?

With schema description coverage at 0%, the description was expected to compensate, but it only hints at campaign_ids as the batch parameter. It leaves campaign_id and auth_account unexplained and does not clarify whether campaign_id is still needed when campaign_ids is supplied, which is a real invocation ambiguity.

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 'Permanently delete a Meta Ads campaign', a specific verb + resource statement that unambiguously identifies the tool. It is clearly distinct from sibling tools like meta_ads_campaign_write_pause/update and other *_delete tools by naming campaign as the object.

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?

The 'Irreversible' warning implies a destructive intent and suggests not to use this when a pause/update would suffice, but the description never directly names alternatives or states when not to use it. The bulk-support note gives some usage context, yet there is no explicit guidance around replacing with meta_ads_campaign_write_pause for temporary stops.

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