mhlb_update_order

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

The description discloses that the write is UNVERIFIED and derived from a compiled API client rather than tested against a live account — a critical caveat for an agent deciding whether to trust the operation. It also reveals the endpoint replaces the entire order (not a patch) and that confirm=false yields a preview. These go well beyond the sparse annotations (readOnlyHint: false, openWorldHint: true) and align with them, adding significant context.

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, each earning its place: the action and replacement model, the mandatory pre-call for the model, and the critical unverified warning. The most operationally important fact (replacement vs. patch) is front-loaded. No redundant phrasing or repetition of schema fields.

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?

The description fully explains the end-to-end flow: retrieving the model, editing, previewing, confirming. The absence of an output schema is mitigated by the explicit mention of the dry-run preview. It does not describe post-confirmation return values or error states, but given the unverified disclaimer and the preview gate, an agent has enough to safely call it. A 4 is appropriate; a 5 would require a bit more about what happens after confirm.

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?

The input schema already documents both parameters with accurate descriptions (order model from get_order/get_order_form; confirm boolean). The description adds value by explicitly instructing to 'send that model back' with edits, making the round-trip pattern clear and explaining that the order parameter must be the full returned object, not a partial. Schemas cover 100%, but the description enriches the meaning beyond the property definitions.

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 description opens with 'Change an existing lunch order', a specific verb and resource that immediately distinguishes it from mhlb_create_order and mhlb_delete_order by the word 'existing'. It also states the replacement semantics ('replaces the whole order') which clarifies the scope. No ambiguity remains about what the tool does.

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?

The description gives an explicit workflow: call mhlb_get_order first, send that model back with edits, and confirm only after inspecting the dry-run preview. It names the prerequisite sibling tool and the required confirm step, leaving no room for missue. It also implies the when-not-to-use by requiring an existing order, which no other sibling covers this directly.

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