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

Goes well beyond the annotations: it states that nothing in the CRM changes, that the action_id becomes unconfirmable, that unconfirmed previews auto-lapse after 30 minutes, and that a linked account with the agent's own CRM permissions is required. This is meaningful behavioral and auth context the structured fields do not carry, and it is consistent with destructiveHint=false and idempotentHint=true.

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 the core effect, then the auto-lapse rule, then the auth prerequisite. The 'and the agent does not want' clause is slightly awkward but every sentence carries information; minor trimming would help.

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?

An output schema exists, so return values need not be described, and the annotations already cover the safety profile. What remains for a mutate-ish tool — whether anything changes, what happens to the id, expiry, and auth requirements — is all stated. An agent has everything needed to invoke it correctly.

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 100% and the single action_id parameter is already documented ('The action_id from the preview'). The description reinforces that the id relates to a preview but adds no new format or syntax detail, so the baseline 3 applies.

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 ('Drop') and resource ('a change you staged'), and the phrase 'can no longer be confirmed' implicitly draws the boundary against the sibling confirm_action. An agent can tell what this does and which operation it is the inverse of.

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 a clear when-to-use condition ('a change you staged and the agent does not want') plus a prerequisite (linked PropertyList account, agency API key alone insufficient). It also notes that an unconfirmed preview lapses after 30 minutes, implying cancellation is unnecessary then. It stops short of explicitly naming confirm_action as the alternative.

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