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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true; the description adds real substance on top by specifying what survives ('Imported orders and settings stay') and giving the exact return shape. It doesn't cover permissions or whether in-flight imports are interrupted, which keeps it from a 5.

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?

Four short sentences, front-loaded with the action, followed by trigger, preservation guarantee, return shape, undo path, and parameter provenance. Nothing is redundant and the most decision-critical facts come first.

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?

With only two parameters and no output schema, the description supplies everything needed: trigger condition, side-effect scope, return field list, and the inverse tool. An agent could invoke this correctly without opening the schema.

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 coverage is 50% – connection_id is documented in the schema itself, and project_id has no description. The description restates the connection_id source (already in the schema) and labels project_id 'OPTIONAL', which the required list already implies, without explaining what scoping by project does.

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 and resource with scope: 'Turn OFF order syncing for a standalone order connection.' The word 'standalone' implicitly separates it from the marketplace order-sync siblings, but it never names stop_marketplace_order_sync or sync_project_orders as contrasts, so the agent must infer that boundary.

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?

Directly states the triggering intent ('when the user wants a connection to stop importing orders') and pairs it with the inverse tool: 'Undo with activate_order_connection.' No explicit when-not guidance is given, but for a binary on/off toggle the alternative is unambiguous.

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