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

Goes well beyond the annotations: quote_id validity of 24 hours, the two distinct payment paths (Claude/ChatGPT always returns a payment link and never charges a saved card; API-key/app callers with payment.saved_card.usable charge immediately and must confirm within 15 minutes), and the explicit guarantee that nothing is ordered or charged by this call. It also discloses negative scope (warm-up is never offered/sold/priced, no plan needed), which is the kind of constraint annotations cannot express.

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-loaded with the purpose and alternatives, which is good, but the middle sags: the return fields are enumerated twice ("The answer has quote_id ... due_today_cents ..." and later "Show the user the full quote (every domain with its first-year and renewal price ...)"), which is repetitive and partly redundant given an output schema exists. The long payment-routing and warm-up sentences are useful but could be tightened.

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 six-parameter quoting tool that sits in front of a purchase, an agent has everything needed to call it correctly, interpret the quote, and route payment behavior. It over-explains return values that an output schema already covers, but nothing an agent needs to act safely 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 100%, so the baseline is 3, but the description adds real meaning the schema does not: the conversion rule "each mailbox sends 5 a day" that links daily_volume to mailboxes, and that mailboxes come in bundles of 100 across 2 domains. The remaining parameters (billing, currency, company) are covered adequately by the schema descriptions.

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?

"Get a price for new mailboxes on their own new domains, for cold email" names a specific verb (price/quote) and resource (mailboxes on new domains) and immediately scopes it as a pre-order step. It is clearly distinguishable from argorant_order_inboxes and argorant_suggest_inbox_domains, which are named in the same sentence.

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 an explicit ordering relationship ("Use it before argorant_order_inboxes, which orders exactly one quote") and an explicit alternative for a different intent ("for other domain names use argorant_suggest_inbox_domains"). It also states how to invoke it (exact domains, a company/brand, or both) and the human-in-the-loop requirement (show the full quote, order only after explicit yes).

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