upsert_manufacturing_order

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

With no annotations, the description carries the full burden and does so: it declares the legacy immediate-write status, the safe-writes bypass, and high risk up front, then documents partial-update semantics (unmentioned fields preserved, output line patched in place, inputLines merged by id or unambiguous productId, deleteInputLineIds removed). This is unusually rich disclosure for a mutation tool.

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 critical warning and redirect are front-loaded before any mechanics, and every subsequent sentence adds substantive merge/patch semantics. Dense but zero waste for a 19-parameter upsert.

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 19-param, nested-object mutation tool with no annotations and no output schema, the create-vs-update mechanics are well covered. Remaining gaps are minor: optimistic-concurrency expectations (the `timestamp` rowversion) and required-field enforcement for creates are left to the schema rather than explained.

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 74%, above the baseline threshold, and the description still adds real meaning: it explains that `id` switches create vs update mode, that `inputItems` is create-only, that `inputLines[]` merges rather than replaces, and that `outputSerialNumbers` patches the parent output line (pass [] to clear). It stops short of covering concurrency (`timestamp`) behavior in prose, which the schema handles.

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 and covers both modes explicitly: 'Create a new manufacturing order or update an existing one,' with the update branch triggered by `id`. It also names the sibling it supersedes, so the agent can distinguish it from set_manufacturing_order without opening either 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?

Opens with an explicit redirect ('Use set_manufacturing_order instead') and a risk flag, then gives the exact condition that selects each mode (`id` present = partial update, absent = create). Both when-to-use and when-to-avoid are stated, nothing 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.