tastytrade_prepare_spx_spread

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

No annotations are provided, so the description is the sole behavioral source. It reveals that the tool does not submit the order and that it normalizes input for both backtester and exact-leg simulation, which is useful. However, it does not disclose whether it validates inputs, checks symbol existence, or what happens with invalid spread configurations. For a non-annotated tool, this leaves key behavioral aspects implied rather than stated.

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 a single sentence that front-loads the types of spreads and the core output (backtester and exact-leg simulation requests) and ends with the critical non-submitting behavior. It is concise and accomplishes its purpose in one breath, though it could have added a brief list of outputs for even faster scanning.

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 (deeply nested schema over four spread families, multiple simulation paths, and no output schema), the description is minimal. It does not mention the distinction between backtester and exact-leg simulation, nor the validation or normalization steps, nor what the return value looks like. Siblings like tastytrade_simulate_spx_spread and tastytrade_create_spx_spread_backtest exist, so an agent needs to know what this returns to use it as a prerequisite. The description is not sufficient on its own.

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?

The schema has 0% description coverage, but it is an extremely detailed schema with nested properties, enums for family/action/price_effect, and even a backtest_selector object. The description only says 'normalize' and lists the spread types, which adds minimal value beyond what the schema already shows. It doesn't explain the distinction between the backtest and exact-leg outputs, nor does it clarify the interplay of fields like backtest_selector and days_until_expiration. The schema carries most of the semantic burden, so a baseline 3 is appropriate.

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 the tool normalizes SPX spread variants (debit/credit vertical, iron condor, double diagonal) into two specific kinds of requests (Backtester and exact-leg simulation), and explicitly notes it does not submit the trade. This distinguishes it from siblings like tastytrade_simulate_spx_spread (which submits) and tastytrade_create_spx_spread_backtest (which creates a backtest).

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 says 'normalize... without submitting it' but does not explicitly state when to use it versus alternatives like tastytrade_simulate_spx_spread (which presumably submits) or tastytrade_create_spx_spread_backtest (which creates a backtest). An agent must infer that this is a preprocessing step, but there is no explicit guidance on when to call this first versus directly calling the simulation/backtest creation tools.

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