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

Annotations indicate destructiveHint=true, aligning with the description's clear statement of a multi-step action that deposits, borrows, and sells (destructive operations). The description adds significant behavioral context beyond annotations: it reveals the ordered step plan output, authenticity verification, geo-gating rules, and idempotency behavior. It doesn't contradict annotations; rather, it enriches them with details about the process and requirements.

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 detailed but organized: the opening line gives a clear summary, followed by a concise description of the return value, then a dedicated paragraph for jurisdiction, and finally a short note on idempotency. While long, it front-loads the most critical information (what it does, what it returns) and keeps details in separate, readable paragraphs, making it efficient for an agent to parse.

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?

Given the tool's complexity (16 parameters, no schema coverage, no enums), the description is remarkably complete. It covers output format (ordered step plan, base64 txs, entry price, health factor, short_id), execution details (authenticity verification, payment requirements), and critical constraints (geo-gating, idempotency). While it omits some parameter specifics, the overall guidance is sufficient for an agent to understand and invoke the tool correctly.

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?

With schema description coverage at 0%, the description must compensate, and it does for several key parameters: it explains jurisdiction (with country code and geo-gating details), idempotency_key (UUID for replay), and allow_unverified (risk warning). However, it does not explain other parameters like token_to_short, collateral_token, collateral_amount, borrow_amount, wallet_address, market, protocol, slippage_bps, etc., which are critical for execution. The lack of coverage for these essential parameters is a gap.

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 clearly states a specific action ('Open a lending-based short') with a clear resource (lending-based short) and explicitly describes the mechanism (deposit collateral -> borrow token -> sell). It distinguishes itself from sibling tools like short_close, short_status, and perp_open_short by focusing on the lending-based open action.

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 states when to use this tool (to open a lending-based short) and provides important constraints: authenticity verification, geo-gating with jurisdiction requirements, and idempotency for retries. It implicitly differentiates from perp_open_short by specifying 'lending-based' and mentions alternatives like declare_jurisdiction for jurisdiction setting. While it doesn't list all alternatives, the context is clear.

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