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

It goes well beyond the annotations: the tool is a queued job returning {id, state: queued}, costs $2 USDC on Solana via x402, a failed run is rerun free on the same id, only graduates are filled, bonding-curve picks land in skipped_not_covered, and the most recent eight weeks are returned separately. The readOnlyHint is defensible for a pure simulation, but the description usefully discloses the job creation and payment side effects the annotation does not capture.

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?

Purpose and inputs come first, then the queue/payment mechanics, then the polling instruction — good front-loading. The prose is dense and slightly convoluted in places ('what they made, pick by pick and in sum, every pick counted, the dead ones included'), but nearly every clause carries operational information.

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 5-parameter tool with a nested exit object and no output schema, the description covers the return shape ({id, state}), the follow-up tool, the payment handshake, coverage gaps, and cost. Nothing an agent needs to invoke it correctly is missing.

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%, so the baseline is 3, and the description adds real value by defining which picks are valid ('bonding-curve picks, and picks outside the archive, are counted in skipped_not_covered') and by tying latency_s to the fill ('filled at the PumpSwap pool as it stood after your latency'). It does not elaborate on the exit object's take/trail interplay, but the schema already documents those fields.

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 names a specific verb and resource ('Backtest pump.fun picks') and goes further to specify the fill model (PumpSwap pool after latency), fee handling, and coverage limits. An agent can distinguish it from replay_result, check_coin, or launch_record without opening any 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?

It gives explicit caller intents ('backtest my calls', 'would this strategy have made money', 'replay these picks with real fills') and routes the follow-up step by name: 'poll replay_result with the id'. The queue-job semantics and the payment prerequisite are stated up front, so the agent knows both when to use it and what happens next.

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