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

Annotations already flag this as non-read-only, destructive, and open-world, but the description adds idempotency and recovery semantics beyond them: single-shot confirmation, token expiry bounds, prohibition on replaying by name, and prohibition on preparing a replacement copy. This is exactly the mutation-safety context an agent needs and cannot get from the annotations.

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?

Front-loads the action and return values, then the sequencing and safety rules, in four tight sentences with no filler. Every clause (single confirm, poll target, uncertainty fallback, lost-response recovery) carries operational weight.

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?

No output schema, but the description covers returns (one operation_ref and task_ref) and the follow-up polling tool, and the annotations carry the safety profile. The only gap is that the optional connection_context parameter goes entirely unexplained.

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 full parameter burden. It adds real meaning for confirm_token (it comes from the prepare step, is expiry-bound, and must be reused exactly to recover the same task), but says nothing about connection_context, leaving one of two parameters undocumented in both schema and prose.

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 concrete verb and resource ('Confirm a prepared copy/bulk-append plan') and ties it to the required confirm_token, so an agent knows this executes a previously prepared plan rather than creating one. It is clearly separable from the prepare sibling (copy_ad_quick_copy) via the word 'prepared', though no sibling is named explicitly.

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?

Explicit routing rules: confirm once, then poll tasks_get_status; when uncertain consult operations_get on the original route; never replay or recover by name; if the response was lost reuse only that exact token within its original expiry. It names the alternatives and the exact conditions that select them.

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