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

Annotations already indicate mutability and open-world behavior, but the description adds crucial behavioral detail beyond them: the tool returns an authUrl for the user, does not handle credentials, can return 'auth_required' or 'rejected', may raise the monthly bill, and may require a plan upgrade. This is exactly the kind of side-effect and workflow context an agent needs and the structured fields do not provide.

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 long, but every sentence carries decision-critical information: what the tool does, what it does not do, user action required, return shape, cost consequences, plan upgrade possibility, and post-auth workflow. It is front-loaded with the most important trait (no credential handling) immediately after the purpose statement. Slightly dense, but justifiably so.

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?

Given there is no output schema, the description remarkably covers the return object's key fields, possible statuses, cost impact semantics, the upsell/plan-upgrade case, and the expected next steps after authentication. An agent has enough information to call the tool correctly, interpret its response, and avoid a costly or dangerous action.

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 only 50%, so the description must compensate for the undocumented project_id parameter. It does so by explaining project_id is optional and that list_projects should be called when it is required. It also reinforces channel_api_code's origin from list_order_channels, adding practical sourcing meaning beyond the schema text.

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 opens with a specific verb and resource: 'Start adding a standalone order connection for a channel from list_order_channels.' It clearly distinguishes itself from related siblings by emphasizing that it does NOT create or authenticate the connection itself, but returns a user-facing Koongo UI link. This makes the tool's role unambiguous even without opening the schema.

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 gives clear context for when to use the tool: when starting a standalone order connection, and it explicitly instructs that the assistant must not handle credentials and must get user confirmation before opening the link when costImpact.willIncrease is true. It also names the project_id-required fallback (call list_projects) and the follow-up tools (test_order_connection, configure_order_connection), though it does not formally state exclusions versus all alternatives.

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