q402_yield_withdraw

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

With no annotations, the description carries full burden and does so thoroughly. It discloses the confirmation gate, sandbox behavior (no real funds unless live key + env var), retry safety (status='uncertain', idempotencyKey replay), server-side key handling, gas sponsorship, and venue reporting. This goes far beyond a typical description.

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 long but all content is purposeful, formatted in scannable uppercase lead-ins ('REQUIRES CONFIRMATION', 'SANDBOX BY DEFAULT', 'RETRY SAFETY') that front-load critical behaviors. It is dense with information but avoids fluff. Slight deduction for length, though nothing is redundant.

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?

Despite having 8 params and no output schema, the description fully covers operational prerequisites (confirmation, sandbox), retry handling (uncertain status, idempotency key), chain/token constraints, and where to find results ('reported in the receipt'). It even references related tools for pre-condition checks. This is comprehensive for a high-complexity transaction tool.

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 baseline is 3. The description adds meaningful context beyond the schema: clarifies amount='max' can be less than full position due to caps, explains consentToken flow, and gives the full retry-safe idempotencyKey semantics ('re-calling with the same key replays the first result instead of double-withdrawing'). This lifts it above baseline.

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 opens with 'WRITE - MOVES FUNDS. Withdraws the Agent Wallet's supplied stablecoin out of its Q402 Yield lending position back to the Agent Wallet.' This names the specific verb (withdraw), resource (Q402 Yield lending position), and direction (back to Agent Wallet), making the tool's purpose unmistakable. It also distinguishes from siblings like q402_yield_deposit and q402_yield_positions, creating clear differentiation.

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?

Provides clear context: 'Use q402_yield_positions first to see the current position size', explicit confirmation workflow ('Call it FIRST without confirm... get explicit approval, THEN re-call'), sandbox default conditions, and chain availability ('Other chains are not yet available'). It does not explicitly name a contrary alternative sibling, but the guidance is concrete and actionable enough to rate above baseline.

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