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

The description frames the tool as a pure read ('Read the selected store's order-reporting connection and saved requests'), yet the annotations declare readOnlyHint=false and destructiveHint=true. It adds nothing about what the destructive behaviour would be, what permissions are required, or what any side effect is. Because the stated behaviour directly conflicts with the declared safety profile, this is an annotation contradiction rather than a documentation gap.

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 short sentences, the core purpose front-loaded, with no filler. The only weakness is that the brevity is achieved by omission rather than by tight wording.

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?

An output schema exists, so return values need not be described. But for a tool with six parameters, a nested arguments object, a session/catalog-version precondition, and destructive annotations, the description leaves the invocation prerequisites and the destructive implication completely 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 50%; read_skills, expected_catalog_version, and publication_proposal_id are already documented in the schema. The phrase 'the selected store' is the only meaning the description adds, loosely mapping to the nested arguments.store_id. It says nothing about work_id, request_key, or whether read_skills is required for this particular read, leaving half the parameters unexplained in both places.

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 (Read) and two specific resources: the store's order-reporting connection and its saved requests. It does not, however, distinguish this from close siblings such as native.genads_store_order_request, native.genads_import_store_orders, or native.genads_check_store, so an agent still has to guess which one retrieves the saved request records versus the connection itself.

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?

'Connecting Shopify is an owner action in GenAds' is a genuine when-not clause, telling the agent this tool cannot be used to establish the connection. Beyond that the description gives no when-to-use condition and never routes the agent to a named alternative for requesting or importing orders, so the guidance is implied rather than explicit.

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