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

Annotations cover idempotency/open-world/destructive, and the description still adds substantial context: the order is not paid until the user opens the link, re-calling for the same quote returns the same order, the delivery address must be in Norway, and the price_pending/kode wait-and-retry behavior. No contradiction with idempotentHint=true or readOnlyHint=false.

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 purpose, then preconditions, then return behavior, then the price_pending edge case. Dense and largely waste-free, though the parenthetical asides make it a touch run-on.

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?

An output schema exists, yet the description still tells the agent what to do with payment_url (user opens it) and how to interpret the price_pending state. For a nested-object order tool with a payment flow, nothing an agent needs 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 75% and the boolean parameters are already documented in the schema, but the description reinforces their operational meaning (terms acceptance tied to the vilkar URL, rights confirmation, details already collected). It adds framing rather than new field syntax, so slightly short of a 5.

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?

Specific verb+resource: 'Place an order for a quote on the user's behalf and get a payment link.' An agent instantly knows this converts a quote into a paid order, distinct from the read-only siblings get_print_quote/get_quote_status.

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?

Explicit preconditions ('Only call this after the user has given you their details and explicitly confirmed that they accept the terms... and have the right to use the model'), plus a named alternative for the pending case ('or poll get_quote_status'). When-to-use, when-not, and the fallback are all stated.

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