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

With no annotations provided, the description carries the full burden—and it delivers. It discloses refusal behavior (no funds moved, only a refusal record), testnet vs. mainnet semantics (simulated vs. real signing, fail-closed), and the constraint that it 'never claims a fill it cannot show.' These are behaviors the agent needs to reason about safety and outcomes.

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 description is dense and front-loaded with the core purpose, then flows into gating constraints, mode differences, and a critical safety directive. Though long, each sentence carries distinct information (refusal, fail-closed, venue registry, user confirmation). No filler; it reads as a structured warning sheet for a high-stakes action.

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 tool with no output schema, the description covers what to expect on success and failure (receipt vs. refusal record), how to handle modes, and which sibling to consult. It also flags the prerequisite (user confirmation) and the risk of stale preview hashes. This is complete for an approval endpoint that must be invoked correctly to avoid financial consequences.

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 100%, so the schema documents each parameter. The description adds flow-level meaning: mode's enum is explained ('Default testnet. Live is fail-closed without a submit path'), executionId is tied to the prior turn, and previewHash is described as binding the signature to the reviewed artifact. This enriches the agent's understanding beyond field-level descriptions.

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 immediately states a specific verb+resource: 'the one call that actually settles a plan from ava_copilot_turn.' This distinct purpose separates it clearly from siblings like ava_preview_tx (preview) and ava_lend_execute (a different execution path). The phrase 'the one call' reinforces its unique role in the approval flow.

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 explicitly routes the agent: 'Call ava_list_venues for which routes are live rather than assuming' and warns 'NEVER call without explicit user confirmation of the previewed quote.' It also explains when a call might refuse, setting expectations for alternative outcomes. This leaves no ambiguity about when this tool is appropriate.

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