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

The annotations already mark the action as destructive and idempotent, and the description adds meaningful behavioral detail: the change never reaches Xero, there is nothing to undo, the action cannot be reversed, and the optional reason is not stored or displayed by Invio. This materially exceeds what the structured annotations alone convey and does not contradict them.

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?

The description is front-loaded with the primary effect and every sentence earns its place for a destructive, irreversible operation. However, some sentences are long and slightly repetitive when emphasizing irreversibility and consent, so it is not maximally concise.

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 is complete for an agent to invoke the tool correctly: it explains the preconditions, what counts as valid consent, where pendingChangeId comes from, the meaning of confirm, the irreversibility, the storage behavior of reason, and the manual alternative. Given the high stakes and no output schema, there are no meaningful gaps.

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 all parameters at 100% coverage. The description adds important usage semantics: confirm must be true and only after explicit consent, pendingChangeId must come from list_pending_changes or a draft-creating tool and never be invented, and reason is not persisted. This goes beyond the schema even though much of it reinforces what the schema says.

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 and resource: it rejects a pending change that was proposed to Xero but never actually sent. It clearly describes the consequence (discarded, never reaches Xero, irreversible) and is easily distinguishable from the sibling approve_xero_pending_change and list_pending_changes.

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?

Provides explicit when-to-use guidance: only after the user has clearly said, in their own words, to discard this specific change. It also tells the agent what not to do (never infer consent from silence or topic changes), suggests calling list_pending_changes first if the summary isn't in conversation, and notes that the manual Invio Settings path remains available.

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