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

Annotations only cover the generic safety profile (non-readonly, non-destructive, non-idempotent, closed-world). The description goes well beyond that: the invoice is numbered in the user's sequence, it inherits saved business details, it is not sent, and free plans are capped at 3 invoices versus unlimited on paid plans — a quota limit an agent cannot infer from any structured field.

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?

Front-loads the core action and required inputs in the first sentence, then packs prerequisites, side effects and plan limits into three dense follow-ups. Every sentence carries information, though the plan-quota sentence is slightly tangential to invocation.

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 a 9-parameter mutation tool and no output schema, the description covers the important invocation context: required inputs, prerequisites avoided, numbering/business-detail side effects, and draft (not sent) state. It does not indicate what the call returns (e.g. an invoice id or number) that a caller would need to subsequently pay or send it, which is the remaining gap.

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 56%, with the schema itself documenting unitPrice, dueDate, dueInDays, issueDate and clientEmail. The description adds useful meaning for clientName and items (no saved client required, one or more line items) but says nothing about notes, clientAddress, vatRatePercent or item quantity/description, leaving a meaningful portion of the 9 parameters undocumented here.

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 ('Create and save a draft invoice') plus the minimum inputs required, and scopes it to the signed-in person's TapTax account. This clearly separates it from siblings like send_invoice, list_invoices and generate_invoice_numbers, all of which could otherwise be confused with invoice creation.

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 tells the agent it does not need a saved client, a prior invoice or a client email, and that the email only matters later for sending — which implicitly routes the agent to send_invoice for delivery. It never names that sibling or states exclusions in tool-name terms, so it stops short of a full when/when-not routing rule.

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