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

Goes well past the annotations: discloses that a worker (not the call) generates each invoice, that draft leaves each for review while send emails on the day, that paused schedules skip missed dates, and that cost is $0.001 per call with no charge on failure. It is consistent with readOnlyHint=false and idempotentHint=false, and the partial-update semantics clarify why repeated calls with repeating_id are not idempotent.

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?

Dense but almost every clause carries information an agent needs (cadence, action, placeholders, update semantics, cost). It is a single run-on block with semicolons rather than front-loaded structure, which makes scanning harder than it needs to be, but there is no filler.

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?

Covers the creation/update lifecycle, scheduling semantics and billing cost, which is a lot for an 18-parameter tool. The main gap is the return value: with no output schema, the description never says whether the created schedule's repeating_id is returned, even though it tells the agent to use repeating_id for later changes.

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 83%, so the schema already documents most fields; the description adds real value on top by explaining the end_date vs times interaction, the action draft/send meaning, and the placeholder grammar ([Month], [Month+1], [Quarter]) that applies inside descriptions and notes but is not captured in the schema. It says little about currency, tax_exemption or e_invoice, which the schema already handles.

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 concrete verb and resource ('an invoice made again every so many weeks, months or years') and anchors it to a known concept (Xero repeating invoices). It also differentiates the create path from the update path via repeating_id, so an agent can tell this apart from invoices_create and invoices_update without opening the 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?

Explicitly covers the two modes: omit repeating_id to create, pass repeating_id to change only the fields supplied, and use status paused/active to stop or resume. It does not name sibling alternatives such as invoices_create for one-off invoices or invoices_delete_repeating, and the 'as for invoices_create' phrase is about parameter shape rather than when-to-use.

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