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

Goes well beyond the annotations by disclosing the fee model (no Panda fee), the refusal threshold, the return contract (unsigned transactions in order plus an EIP-5792 batch), simulation source (simulated from the wallet), and a sign_url path for a human owner. The 'Nothing is sent' statement resolves the apparent tension between the withdraw name and readOnlyHint=true, confirming this only builds transactions.

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?

Front-loads the action and target market, then layers the guardrail, fee, and return format in tight sentences. No filler and no restatement of the tool name or title.

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?

Although there is no output schema, the description fully specifies the return payload (ordered unsigned txs, EIP-5792 batch, sign_url) and the failure condition, so the agent knows both what comes back and when the call is rejected. Nothing material is missing for a 2-parameter build 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 description coverage is 100%, so both parameters (wallet, amount_weth, including the "all" sentinel) are already fully documented in the schema. The description adds no parameter-level format or edge-case detail beyond that, so the baseline 3 applies.

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 (withdraw), resource (WETH collateral), and disambiguating scope (the Morpho WETH/USDC market), which cleanly separates it from siblings like build_lend_withdraw, build_vault_withdraw, and build_borrow. An agent can identify the exact position type being acted on without opening the schema.

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?

Gives a concrete precondition/refusal rule (refused past 86% LTV) that tells the agent when this call is valid versus when it will fail. It does not explicitly name alternative tools or required prerequisites (e.g., an existing borrow position), so it stops short of full when/when-not/alternatives guidance.

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