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

Annotations already mark destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the description's job is to add context beyond those flags. It does this exceptionally well: hard-delete vs soft-delete is conditional on publish history, the response's soft_deleted flag tells which case occurred, the campaign stops appearing everywhere, and importantly, 404 is returned both for unknown ids and cross-workspace access so existence is not leaked. This is rich behavioral disclosure.

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 sentences with zero wasted words. The core action is front-loaded, then the soft-delete nuance and 404 behavior follow logically. Every clause earns its place by conveying behavior an agent needs to know before calling a destructive operation.

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 destructive tool with no output schema, the description covers the critical behavioral surface: what gets deleted, the conditional soft-delete semantics, the response indicator, and error behavior. The primary gap is the unexplained required `idempotency_key` parameter; secondary gaps are the undocumented `brand_id` and `query` params. The workspace_id guidance is already present in the schema itself, so that gap is covered elsewhere.

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 only 40%, below the 50% threshold, so the description must compensate. It marginally helps by implying `id` is the campaign identifier ('Returns 404 for unknown ids'), but it never explains the required `idempotency_key`, nor `brand_id` or `query`. A required parameter with no semantic explanation in either the schema or description is a notable gap for an agent deciding how to invoke this tool.

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 uses a specific verb-resource pair ('Delete a content campaign') and immediately differentiates this tool from the many sibling delete tools by naming the exact resource type. It goes beyond a simple statement of purpose by explaining the two deletion modes (outright removal vs soft-delete) and the 404 behavior, which makes the tool's function unmistakable.

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 resource type makes the intended use case clear — when an agent needs to delete a campaign, this is the tool. However, there is no explicit guidance on when not to use it or how it compares to the many sibling deletion tools (delete_draft, delete_webhook, etc.). The when-to-use context is implied rather than stated, and no alternatives are named.

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