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

Annotations declare destructiveHint=true, but the description supplies the detail the annotation cannot: exactly what is destroyed (the existing note or tags are REPLACED, not merged) and how to avoid it (read first). It also discloses the domain constraint that line items are immutable after creation.

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 sentences, front-loaded with 'WRITE', each carrying distinct payload: operation, overwrite warning, endpoint. No filler or restatement of the title.

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-parameter mutation with no output schema, the description covers operation, replacement semantics, the read-before-write precaution, and the immutability boundary. Nothing an agent needs to avoid data loss is missing.

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%, so 3 is the baseline; the description still adds value by framing note/tags as 'and/or' — clarifying that at least one of the two optional fields should be supplied — and reinforcing replace semantics. It doesn't cover value formats or limits beyond what the schema already states.

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 (WRITE / set) and resource (an order's note and/or tags), plus the endpoint PUT /admin/orders/{id}.json. It also pins the scope by noting that items and quantities stay fixed, which separates it from any sibling in the list.

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 pre-call guidance: read the order first so existing values are not lost. It also implies an exclusion (items/quantities cannot be modified). It does not name the sibling to use for that read (sapo_get_order), which keeps it short of a 5.

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