Retry a FAILED order (write)

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that this is a write operation gated behind AIOTIC_MCP_ALLOW_WRITES, but says nothing about side effects, idempotency, whether the retry re-enters the ERP pipeline, or what happens on repeated retries of the same request_id.

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 with no padding, and the endpoint is front-loaded. It is efficient, though the write-gate sentence is the only thing beyond a bare route string, so brevity shades into under-specification.

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 mutation tool with no annotations, no output schema and an undocumented parameter, the definition is too thin: it omits state-transition semantics, error behavior for non-failed orders, and any indication of what a successful retry returns.

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 0%, so the description must compensate, yet it only embeds request_id as a URL placeholder in the path template. It never explains that this identifies the original order request (e.g. from upload_order) or whether it must reference a currently-failed submission.

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 name and title ('Retry a FAILED order (write)') give a specific verb, resource and the state precondition (FAILED), and the description supplies the concrete endpoint POST /order/retry/{request_id}. It is distinguishable from siblings like upload_order or send_order_to_erp, though the description body itself never restates the purpose and does no explicit sibling differentiation.

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?

'Requires AIOTIC_MCP_ALLOW_WRITES=true' is a real precondition, and the title implies the tool applies only to FAILED orders. However, there is no guidance on when to choose retry_order over upload_order or send_order_to_erp, nor what to do if the request is not in a failed state.

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