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

Annotations only declare the generic profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=false). The description goes well beyond them by stating nothing is charged or placed, that a draftId is returned for later confirmation, the auth prerequisite, and the concrete failure modes (venue closed, no delivery coverage, address outside area).

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?

Front-loaded with the core action and what is returned, then flows into prerequisites and parameter mechanics. It is dense but readable; the only real waste is the repeated non-placement clause ('without placing it' / 'WITHOUT placing anything'), which is redundant emphasis.

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 an 8-parameter mutation-style tool with no output schema, it covers auth, prerequisites, cross-tool id sourcing, side effects, failure modes, and even the shape of the return (draftId, items, fee, total, distance, ETA). Nothing an agent needs to call it correctly 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 only 63%, and the description compensates by explaining the selectedOptions structure (group name + choice name, required groups must be chosen), that deliveryAddress should be the fullest address available, and that savedLocationId is used instead of it. It leaves restaurantId, guestName and guestPhone unglossed, so it falls short of fully covering the gap.

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 ('Drafts a food/drink DELIVERY order without placing it') and enumerates exactly what the draft contains: priced items, delivery fee, total, distance and ETA. It explicitly names the two siblings that finish the job (confirm_delivery_order, place_delivery_order), so an agent can distinguish them without opening a 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?

Gives explicit routing rules: use confirm_delivery_order to place a draftId, or place_delivery_order for both steps, and notes the latter follows the connection's permission setting. It also states the prerequisite (WaitApp account connected), a validation step (verify venue city/countryCode via search_venues), a data source (list_menu_items for ids/optionGroups) and the required-option rule (required=true must be chosen).

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