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

With destructiveHint=true already set, the description adds real context: the two possible outcomes (active once bought, pending while payment clears), that consent must be the same object given at the start, and a mandatory disclosure/affirmation gate. It says nothing about payment failure, retries, or double-charge risk when the tool is re-called on a session, which matters for a financial mutation. The description also softens the write into "check on a purchase," which reads less consequential than destructiveHint implies.

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?

The critical instructions are front-loaded in the first two sentences, but the third block dumps eleven verbatim disclosure bullets into the tool definition. Those are already delivered at call time via the quote's required_disclosures (the description even says to read them from there "word for word"), so the inline copy is largely duplicated payload that buries the actual call instructions.

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 destructive, no-output-schema purchase tool, it covers when to call, the pre-purchase workflow and the disclosure gate, and even hints at the response shape (active vs pending). What's missing is error and retry behavior for a payment session — the one thing an agent will need when the call doesn't resolve cleanly.

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% and the nested PurchaseConsentInput documents each field (terms_versions, disclosure_set_id, disclosure_text_sha256, affirmations) with formats and echo semantics, so the baseline is 3. The description restates payment_session_id's origin but adds no meaning beyond the schema for quote_id or the consent payload, though it does clarify that consent is required to start and optional when finishing.

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 opening sentence names a specific verb and resource ("Finish an in-conversation purchase") and pins the input it needs (the payment_session_id the checkout returned), so an agent can tell what it does. It never contrasts itself with the sibling purchase_quote, and the framing then shifts to "call it only to check on a purchase it reported pending," which makes the tool look more like a status poll than a purchase finalizer.

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 when-not ("The checkout calls this itself; call it only to check on a purchase it reported pending") plus a step-by-step prerequisite workflow (collect email, try read_declarations_page, else create_quote, show disclosures first). It stops short of naming the sibling to use for the initial purchase instead of this one, so the routing decision against purchase_quote is left implicit.

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