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

Annotations only declare the write/destructive/open-world profile; the description adds the refused-operation error code, the required `x-otto-delegation-auth` header, the withdrawal fence and ruleset-v2 consent conditions, sequential reset/approval/call submission with canonical receipts and allowance clearing on halt, and an explicit no-retry policy for uncertain prior operations. This is far more behavioral context than the annotations supply.

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 opening sentence is well front-loaded, but the body is a dense run-on mixing retirement policy, argument list, fence rules, retry policy and sibling routing into long compound sentences. Most content earns its place but could be split or trimmed; density hurts scanability.

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, so return values need no explanation, and the description covers auth, qualifying conditions, sequencing, halt behavior, error codes and the no-retry boundary. It is nearly complete for a destructive, auth-gated submission tool, with only minor gaps such as types for the envelope/prepareInput payloads.

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?

The declared schema has no properties, so the description carries the entire parameter burden and does name the arguments ({ userId, envelope, prepareInput } with slippage.minAmountOut) plus the validation constraints on output token, spender, share amount and receiver. It does not give types or formats for userId/envelope, but it adds real meaning beyond an empty schema.

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+resource: submitting a qualified Model B vault withdrawal, plus replaying an existing terminal result. It explicitly carves itself out from the retired trading path and from prepare-only tools, though the opening two sentences about retirement front-load context before the actual purpose. An agent can identify what the tool does and roughly where it sits among siblings.

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?

Explicitly states that new delegated trading is refused (DELEGATION_TRADING_RETIRED) and that prepare-only tools remain available, and routes uncertain prior operations to 'delegation operations/reconciliation'. It also notes status/revoke/qualifying exits live elsewhere. There is no positive 'when to use this instead of X' statement, but the exclusions are unusually rich.

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