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

Beyond annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=true), the description richly discloses side effects: the install requires human approval, the AI chat appears automatically, the agent learns products/policies, sends add-to-cart links, gives order status, and notifies owners of sales. This goes well beyond the annotations and paints a transparent picture of the tool's behavior and consequences.

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?

The description is fairly long but well-structured, starting with the overall scope and then detailing each action. Every sentence contributes meaningful information, especially the workflow and consequences. It could be slightly trimmed, but the density of required behavior justifies the length.

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 tool with three distinct actions and no output schema, the description covers the essential context: what each action returns (lists, link, re-read), the approval flow, and the resulting capabilities. It doesn't mention error handling or edge cases, but these are not typically required in a description. The coverage is solid for the tool's complexity.

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 67%, covering shop and store_id. The description adds meaning by explaining that store_id comes from status, that shop is specifically for install_link, and elaborates on the action enum values which the schema does not describe. This helps an agent understand parameter usage beyond the terse schema descriptions.

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 clearly states the verb 'Connect' with the resource 'Shopify store' and enumerates three specific actions (status, install_link, sync). It distinguishes itself from sibling tools like oryksa_status or oryksa_links by focusing exclusively on Shopify store connection and management.

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 description provides explicit context for each action: status lists connected stores, install_link returns the approval link, sync re-reads a catalogue. It also notes that a person must approve the install, which is crucial operational guidance. However, it does not explicitly contrast with sibling tools or specify when not to use this tool, though the purpose is clear enough.

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