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

With annotations already declaring readOnlyHint=true and destructiveHint=false, the description still adds substantial non-obvious behavior: it builds unsigned transactions for the wallet to sign, requires a gas limit of at least 12,000,000 because the transaction carries gas, enforces hook and sale-price thresholds, stops at desk capacity, and stalls while the desk is paused. Crucially, 'Unsigned transactions ... Simulated from the wallet' explains why a state-changing short appears as a read-only prepare step, so there is no tension with the annotations.

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 core action is front-loaded in the first clause, and the remaining conditions are packed densely with little waste. It is a single long, comma-chained paragraph and a phrase like 'its transaction carries gas' reads awkwardly, but no sentence is filler.

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 prepare-style tool with three parameters and no output schema, the description covers the important ground: what is returned (unsigned transactions simulated from the wallet), the gas requirement, the success thresholds, capacity limits, and pause behavior. It does not spell out the shape of the returned transaction list or what a partial/failed simulation looks like, which is the only notable gap.

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%, which sets a baseline of 3, but the description adds real meaning: 'amount' is what gets borrowed and sold, and the optional 'deposit' is USDG approved alongside it with the sale proceeds joining that deposit. That clarifies the interaction between the two money fields and the conditional nature of the deposit beyond the schema's terse 'USDG to deposit with it'.

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 opening clause names a specific action and resource: 'Unsigned transactions to open (or add to) a gAIX short from the wallet', and the mechanics (borrow gAIX, sell through Goldstein's pool, proceeds join the deposit) further pin down what the tool does. This distinguishes it cleanly from siblings like gaix_short_close, gaix_short_deposit and gaix_short_quote without needing their schemas.

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 gives concrete conditions governing whether the call goes through (hook at most 2%, sale at least 95% of gAIX price, capped at the desk's room and three quarters of the limit, waits while the desk is paused) and notes that the USDG approval is included 'when needed', which tells the agent when the tool will and won't succeed. It never names an alternative sibling (e.g., quoting first with gaix_short_quote or closing with gaix_short_close), so routing guidance stops short of a 5.

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