Send order to ERP (dangerous)

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

With no annotations, the description carries the full load and does disclose non-obvious traits: this is a POST that leaves the system and calls a third-party tenant ERP endpoint, and it is double-gated by an environment flag and confirm:true. It stops short of stating idempotency, error behavior, or whether a repeated call is safe.

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?

One compact sentence: endpoint and external target first, then the two gating requirements. Nothing is padded and the critical constraint is not buried.

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 dangerous external mutation with no annotations, no output schema, and 0% parameter documentation, the description omits failure behavior, idempotency/retry semantics (notable given a retry_order sibling exists), and the expected order state. An agent can gate the call but cannot reason about consequences.

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. It does clarify confirm:true as a gate (the schema only shows default false) and the path template shows request_id goes in the URL, but it never explains what request_id identifies or which order state it must reference.

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+resource ('send order to ERP') and pins the exact endpoint (POST /erp/send/{request_id}) and the external system involved (the tenant's ERP receive endpoint). It does not explicitly differentiate itself from siblings like retry_order or upload_order, which is the only thing keeping it from a 5.

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?

It gives a hard precondition (AIOTIC_MCP_ALLOW_DANGEROUS=true plus confirm:true), which tells the agent when the call is permitted. However it never says when to choose this over retry_order or upload_order, nor what state the order must be in beforehand, so alternative routing is left to inference.

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