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

Beyond the annotations it discloses the things an agent could not infer: nothing is charged at creation, an unpaid order expires after 24 hours, payment is taken at purchase, delivery lands within hours and always within 6, and invalid details create no order at all. The private nature of orderToken is also called out. It never contradicts the destructiveHint=true annotation; it narrows what creation actually does.

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 is front-loaded correctly and nothing is padded with boilerplate, but the single paragraph is dense and mixes order lifecycle, product input rules, and a lengthy explanation of Y pronunciation without headings or bullets. An agent has to parse a wall of prose to extract the per-product field requirements.

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 16 parameters and no output schema, the description fills every gap that matters: the per-product field matrix, date format, expiry, delivery window, failure mode, and the exact return fields (orderId, orderToken, product, amount, currency, paymentLink, expiresAt, charged). Nothing an agent needs in order to call this 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 coverage is already 100%, so the baseline is 3, but the description adds cross-parameter rules the schema cannot express: which fields each product needs, that name_analysis takes no dateOfBirth, that current-name fields apply only when the name differs from the birth name, and the reading order for yClassifications (first, middle, last; birth name before current name). That is genuine added meaning, though the Y vowel/consonant explanation is longer than the calling decision requires.

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?

The description opens with a specific verb and resource ("Creates an unpaid order for one NumeroClaw reading") and states the outcome (a link to a payment page). It is clearly distinguishable from the siblings get_order and list_products, since this is the only tool that creates a purchase.

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?

It gives explicit preconditions (the person has confirmed product, price, email and details), an exclusion (not for a reading about a child), and a routing rule (one order per person per reading; a second order is a second purchase). It also names the escalation path (email hello@numeroclaw.com with the order id) instead of inventing a retry.

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