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

The annotation declares readOnlyHint=true, but the description says 'Seal a transfer' and 'get back a summary plus a single-use draft_id' – clearly a state-changing creation operation. This directly contradicts the readOnlyHint annotation, which typically signals no side effects. The description does add useful context like 'Moves no money' and 'Any change to amount, recipient, or rail is a NEW draft', but these do not resolve the contradiction.

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 sentences, front-loaded with the core purpose. Every phrase adds value: the action, the output, the non-monetary nature, the device requirement, and the immutability rule. No fluff or redundancy.

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?

The description gives critical behavioral rules ('Moves no money', 'Any change is a NEW draft', 'Requires an active trusted device') and notes the output (summary + draft_id). However, it omits any guidance on what the registered recipient entails, whether parameters are optional, or how to interpret the many optional fields. With an output schema present, return format is covered, but the input context for 8 parameters is largely unexplained.

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 0%, meaning the description provides no parameter-level guidance. With 8 parameters (amountCents, rail, recipientId, sourceAccountId, destinationAccountId, etc.), the description mentions 'amount, recipient, or rail' in a general sense but doesn't map them to specific parameters. The agent is left without any semantic explanation of required or optional fields.

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 description uses a specific verb ('Seal a transfer') with a clear resource (a server-held draft) and states the outcome (get a summary and single-use draft_id). It differentiates from likely alternatives by noting 'Moves no money' and the condition of a registered recipient, making it distinct from commit_transfer and other transfer tools.

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?

The description implies when to use this tool (to create a draft) by stating 'Seal a transfer as a server-held draft' and notes prerequisites (active trusted device, registered recipient). It doesn't explicitly name alternatives like commit_transfer, but its constraints clearly position it as the draft creation step rather than the final execution.

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