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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds substantial behavioral context beyond those: the write hits a live ledger, a failed write cannot be retried (only a new draft can be created), the real outcome must be relayed verbatim, and hesitation does not count as consent. The idempotentHint=true annotation is not contradicted; the one-shot failure description is consistent with idempotent re-execution producing no new effect.

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 long, but the length is largely justified for a destructive approval tool with safety-critical consent rules; it is front-loaded with purpose and then ordered by consent gate, outcome reporting, and the manual alternative. It is somewhat repetitive across the consent warnings ('never infer... never call speculatively... never approve without...'), which could be tightened without losing meaning.

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 a 2-parameter destructive write tool with no output schema, the description covers everything an agent needs: what it executes, the consent precondition, how to obtain the pendingChangeId, failure/retry behavior, what to report back, and the equivalent manual path. The absence of a return-format spec is mitigated because the description explicitly tells the agent to report success and Xero-assigned id/number or the failure reason.

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 100% and both parameters are already fully described in the schema, including the consent gate on confirm and where pendingChangeId comes from ('Never invent one'). The description reinforces these constraints in workflow terms but adds no new parameter semantics beyond the schema, so the baseline of 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 and resource ('Approves a change... and immediately executes it') and names the exact draft-creating siblings (create_xero_invoice, update_xero_contact, etc.) whose changes it acts on. It also carves out its unique role as 'the ONE tool in this connector that actually writes to a live Xero ledger', clearly distinguishing it from list_pending_changes and reject_xero_pending_change.

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 when/when-not guidance: call ONLY after the user has clearly said in their own words to go ahead, never infer approval from context, never call speculatively, and call list_pending_changes first if the summary is not in context. It also names the manual alternative (Invio Settings > MCP > Xero) as an equivalent path, so the agent knows the tool is optional relative to human-approved workflow.

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