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

Beyond the annotations it discloses the exact return fields, the enum-like status values, and that the message is masked and secret-free — security-relevant context an agent would otherwise not know. It stops short of describing failure modes such as timeouts, upstream unavailability, or whether the test itself consumes rate limits, but given readOnlyHint/idempotent hints already cover the safety profile, the added value is high.

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?

Front-loaded with purpose, then return shape, then exception handling, then sibling routing — a sensible order with no filler sentences. It is dense with parenthetical asides and em-dash clauses, which costs a little readability.

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?

There is no output schema, so the description carries the return contract itself and does so precisely (connectionId, status values, masked message). Combined with the auth-completion escape hatch and the pre-activation workflow, an agent has everything needed to call this correctly and interpret the result.

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%: connection_id is documented in the schema, but project_id has no schema description. The description compensates by naming its source ('from get_order_overview'), its optionality, the error condition that makes it required, and the remediation call (list_projects).

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?

Opens with a specific verb and resource: 'Verify that a standalone order connection's saved credentials still work — a live connectivity/auth check.' It also distinguishes itself from near-name siblings by scoping to a single order connection and explicitly disclaiming sync_project_orders.

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?

Gives explicit when-to-use ('before enabling it with activate_order_connection'), when-not-to-use ('do not run sync_project_orders for that'), and a conditional branch ('project_id is OPTIONAL (project_id_required otherwise — then call list_projects)'). It also prescribes agent behavior on the 'not_connected' result: route the user to the Koongo UI, never set credentials via MCP.

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