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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is known. The description adds genuinely new behavior — moving to "done" also closes the linked process step — plus the limits of what "done" via this tool does not include. However, it never explains what destructive means here (e.g., whether cancelling discards work or whether prior status is recoverable).

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?

Three short sentences, front-loaded with the action and status set, followed by side effect and exclusion — no filler. The mixed Portuguese/English phrasing is consistent with the domain but slightly reduces scannability for an English-only agent.

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 3-param mutation tool with rich annotations and a fully described schema, the description covers purpose, a hidden side effect, and an out-of-scope case. Remaining gaps — permissions/auth needs, effect of "cancelled" on the linked process step, and no output schema — are minor but not fully closed.

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 100%, with the enum and per-field descriptions already documenting status and field_order_id (which even points to list_field_orders). The description restates the enum and explains the semantic effect of one value ("done"), but adds nothing about technician_notes or about the consequences of the terminal statuses. Baseline 3 applies when the schema carries the load.

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 (move) and resource (OS / field order) and enumerates the full status domain, so an agent knows exactly what it changes. It does not name sibling tools that also mutate orders (e.g., set_order_stage, update_process_step), so the boundary against those is left to inference.

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?

Explicitly excludes a case: full field closure with mandatory checklist, before/after photos and signature belongs to the technician screen, not this tool. That is real when-not guidance, though the recommended alternative is a UI screen rather than a callable sibling, leaving the agent no tool-level fallback.

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