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

Annotations already flag destructiveHint=true and openWorldHint=true, but the description adds the critical non-structured context: this spends real money for one paid attempt, requires explicit human approval, rejects ambiguous assent, and that a failure/refund voids the old quote so a fresh quote plus new approval is mandatory. That is exactly the kind of consequence disclosure the annotations cannot convey.

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?

Five tight sentences with the gating condition front-loaded before the mechanics, then recovery and retry rules. No filler; every clause either imposes a constraint or points to a sibling tool.

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, money-spending tool with no output schema, the description covers the approval gate, the payload, ambiguous-response recovery, and post-failure policy. The only gap is what a successful call returns (e.g. an operation id to poll), which the agent must discover elsewhere.

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 0%, so the description must compensate, and it does name all four values to send and stresses that amountCents must be the *exact* quoted amount and currency must be USD with confirmed=true. It stops short of explaining the amountCents bounds or the uuid nature of quoteId, which the agent can still infer from the const/format constraints.

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 (submit/confirm) applied to a specific resource (an exactly priced Recast quote) for exactly one paid attempt. This clearly separates it from the sibling prepare_recast (which readies a quote) and get_recast_status (which reads outcome), so an agent can distinguish it without opening any schema.

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?

Gives an explicit precondition ("Submit only after the user explicitly approves the exact fresh Recast quote"), an explicit exclusion ("Ambiguous assent does not authorize spending"), and names the alternative for the ambiguous case (get_recast_status with the same quoteId). It also states the retry rule after failure/refund and forbids auto-preparing a replacement, which routes the agent to prepare_recast.

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