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

Annotations already declare destructive=true, idempotent=true and openWorld=true, so the description needs to explain what recovery actually touches. It contributes useful constraints (no new page fetches, no token exchange, an unconfirmed submitted page blocks freezing a partial report) but never says what state is overwritten or why the operation is destructive, leaving the risk profile vague.

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?

Two sentences, front-loaded with the trigger condition, and the constraint sentence directly follows. The second sentence is dense and somewhat cryptic ('unconfirmed submitted page prevents freezing a partial report') but nothing is wasted.

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?

Output schema is present so return values need not be explained, and the purpose plus key constraints are covered. Against six parameters, a nested arguments object, and a destructive annotation, though, the absence of any parameter guidance or explanation of what gets mutated leaves gaps an agent would have to guess through.

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?

Six parameters with only 50% schema description coverage, and the description mentions none of them. work_id, request_key, and the nested store_id/operation_id arguments are documented nowhere, and the description does nothing to explain how they select the interrupted request, which is exactly where coverage is thin.

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 names a specific verb and resource (recover original captured Shopify pages) and scopes it to a trigger condition (after an interrupted or stopped request). That distinguishes it reasonably well from siblings such as native.genads_import_store_orders, though it never names those siblings 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?

It states the situation that calls for this tool (an interrupted or stopped store-orders request) and adds a hard constraint ('Never fetch another page or exchange a token'). However, it does not say when to prefer this over native.genads_import_store_orders or native.genads_store_order_request, nor what prerequisites (a prior work_id, accepted session) must exist.

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