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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds substantial behavior: fees, priority fee and price impact are included, fills are pessimistic, and the simulation is normalized to 3 SOL capital at 0.1 SOL per trade and 30 trades/day. It also explicitly disclaims 'past data, not a forecast, not advice.' It omits runtime/latency and data-window specifics, keeping it out of 5 territory.

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 content is front-loaded and ends with a clear usage clause, but the opening sentence is a ~110-word run-on covering mechanics, assumptions and return fields at once. It is information-dense rather than wasteful, yet it would be far more scannable split into short lines.

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?

There is no output schema, and the description compensates by enumerating the return values: median final balance, share of replays that ran out of SOL and after how many days, per-trade results, share of winning trades, the median real result of comparable bots, and a chart link. Combined with stated fixed assumptions and the explicit non-forecast disclaimer, an agent has everything needed to call it and set expectations.

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%, with each parameter fully documented with defaults and grids, so the baseline is 3. The description only echoes parameter families ('entry delay, take profit, stop loss, holding time, filters') without adding syntax, ranges, or trade-off guidance beyond what the schema already provides.

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 and resource — 'Simulate / backtest a pump.fun sniper or trading bot' — and immediately scopes it as a pre-deployment risk check. An agent can separate it from siblings like botsharper_test_my_bot or botsharper_check_wallet 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 an explicit trigger: 'Use it when someone asks whether a bot strategy or settings (entry delay, take profit, stop loss, holding time, filters) would make money.' It also frames the tool as pre-risk evaluation, but it does not name a sibling alternative (e.g. test_my_bot) or state when NOT to use it, so it stops short of full routing guidance.

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