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

Despite annotations already flagging destructive/openWorld mutation, the description adds substantial context: async task execution, idempotent token recovery within expiry, that an unavailable token does not prove absence of a task, the shape of a failed terminal response (created objects, failure phase/reason/support_ref, next action), and a legacy recovery path. This far exceeds the annotation baseline.

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?

Content is largely non-redundant and front-loaded with the core confirm action, but it is delivered as a single dense paragraph mixing core semantics with niche edge cases (historical mislabeled UUIDs, legacy tenant-scoped paths). Readability suffers from the lack of structure despite little outright waste.

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 complex, non-read-only, no-output-schema tool, the description covers invocation prerequisites, idempotency/recovery semantics, async follow-up via tasks_get_status, and failure-response shape. An agent has enough to call it correctly and to handle lost or failed responses.

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 coverage at 0%, the description carries the burden and does well for confirm_token: it must come from a prior campaigns_quick_create call and is bound to its original expiry. It also disambiguates task_id from task_ref as inputs. However, the optional connection_context parameter is never explained, leaving one of two params undocumented.

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 ('Confirm') plus the exact resource ('the durable create approval minted by campaigns_quick_create'), immediately distinguishing it from the sibling that mints the approval. An agent can tell it apart from campaigns_quick_create, campaigns_recreate_confirm, and approval_plan_confirm 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?

Explicitly covers when to use (recovering a lost response with the same exact token) and when-not ('do not prepare a replacement'), plus named alternatives for uncertain outcomes (operations_get with operation_ref) and progress watching (tasks_get_status). It even forbids specific wrong approaches ('never replay or name-match').

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