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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new operational context: the cost ($0.01 USDC via x402 with payment in _meta["x402/payment"]), that invalid input errors without charge, and that no network request or storage occurs. These are the kinds of billing and failure semantics an agent must know before calling.

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?

Purpose, return shape, prerequisite, and cost are all front-loaded in an efficient run of sentences with no filler. Minor redundancy between "Draft only: nothing is sent" and "nothing is sent or stored" costs it a point.

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 an 11-parameter, no-output-schema tool, the description covers everything material: the returned fields (subject, body, days overdue, suggested next step), the prerequisite chaining, the side-effect guarantee, pricing, and error/charge behavior. Nothing needed to invoke it correctly is missing.

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 82%, so the schema already documents nearly all 11 parameters (tone, as_of, amount, currency, due_date, etc.). The description adds only the tone concept and the invoice framing, contributing little syntax or format meaning beyond what structured data supplies. 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 (draft), resource (payment reminder email), and scope (one unpaid invoice, three tone modes). It also names the sibling tool late_fee_calc and the condition for chaining, so an agent can distinguish it from invoice_from_timesheet or receivables_health_report without opening schemas.

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?

"Use late_fee_calc first if you want the fee amount quoted" gives explicit sequencing guidance, and "Draft only: nothing is sent" implicitly routes agents elsewhere if they need actual delivery. No explicit when-not-to-use statement or exclusion of other siblings, so it falls short of a 5.

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