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

With no annotations, the description carries the full burden and does real work: it declares the tool only prepares an unsigned transaction ('never sign or send'), names the required sender, and discloses that the withdrawal is all-or-nothing to the destination. It omits failure behavior when nothing is credited and what the prepared payload looks like.

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?

Two tight sentences with the safety constraint front-loaded inside the first clause and the destination default trailing. No filler and nothing buried.

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 transaction-preparing tool with no annotations and no output schema, the description covers safety and destination semantics well, but leaves the agent guessing about chainId selection, the shape of the returned unsigned transaction, and behavior when the balance is zero.

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?

At 67% schema coverage, two of three parameters are documented in the schema and the description largely restates the 'to' default while reinforcing that walletAddress is the sender. chainId is never explained in either schema description or the tool description, which matters for a multi-chain escrow call.

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 and resource: prepare (not sign or send) the transaction that withdraws all credited stablecoin from an escrow wallet. The scope is unambiguous and the 'Escrow v3' prefix situates it. It does not, however, name the sibling read tool (get_withdrawable) that answers the related balance question, so sibling differentiation is only partial.

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 must be sent from that wallet' and the 'withdraws all' framing imply constraints on when and how to call it, and 'default: the same wallet' sets the fallback. But there is no explicit when-to-use versus get_withdrawable, no prerequisite check (e.g. verify a withdrawable balance first), and no exclusion guidance.

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