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

Goes well past the annotations: it clarifies the counterintuitive non-destructive nature of a tool named delete_items, states that a confirmation token is returned with a 10-minute expiry, notes protections are surfaced, and warns the result must be shown to the user. The readOnly/idempotent annotations are consistent with and reinforced by this text.

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?

Four short sentences, each carrying distinct information: trigger, non-destructive behavior, required follow-up, and constraint. The step-1-of-2 framing is front-loaded where an agent will see it first.

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?

With no output schema, the description still conveys the key return artifact (a 10-minute confirmation token) and the two-step workflow. It does not describe the structure of the preview list the agent must show the user, which is the one remaining gap for a preview tool.

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 description coverage is 0%, so the description must compensate. It partially does by naming the deletable kinds (which maps to the kind enum, though journal_note is omitted), but it says nothing about ref, formula, material, or dilutionPct semantics or the 50-item/1-item bounds.

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 (prepare a deletion) and enumerates the six entity types it applies to. It immediately distinguishes itself from confirm_delete by declaring 'it is step 1 of 2 and deletes NOTHING', so an agent can route between the two 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?

Explicit when-to-use ('when the user asks to delete a formula, version, material, bottle, batch or note'), an explicit next step ('only after they agree, call confirm_delete'), and an explicit exclusion ('Locked formulas cannot be deleted here'). Nothing about routing 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.