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

The description adds substantial context beyond the annotations (readOnlyHint, idempotentHint). It states the calculation is deterministic, non-personalised, does not involve a wallet or fee, and is 'not financial advice'. It discloses that the returned suggested_size_usd caps the order in the execute phase, which is critical for safe usage. These details go well beyond the structured hints and align with them perfectly.

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 dense but every sentence earns its place: it opens with a one-line summary, then details inputs, outputs, safety caveats, and workflow in a structured, scannable way. The 'No wallet, no fee' and 'DYOR' notes are valuable for setting expectations. It is front-loaded with purpose and never meanders.

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 complex tool with 6 parameters and an output schema, the description covers the essential behavioral context: what the tool returns, how it should be used, prerequisites ('Check asset_classification first'), and constraints ('do NOT exceed [suggested_size_usd]'). It also names the workflow stage, making the tool fully actionable without needing to inspect external docs.

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 provides no parameter descriptions (0% coverage), so the description must compensate. It explains strategy_type as one of the 16 Crank types, asset as a token mint, timeframe as one of 1m/5m/15m/1h/4h/1d, and references equity as the base for USD notional. However, lookback_candles and caller_id are not explained, leaving a small but notable semantic gap for those parameters.

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 identifies the tool as a combined market regime and risk-guard calculation for a strategy on an asset, explicitly marking it as read-only. It distinguishes itself from siblings like get_token_risk_assessment by describing its unique function of folding risk guards into a single output, and it names related workflow tools (backtest_strategy, asset_classification, get_trading_workflow). The verb 'calculate' and the resource (strategy/asset risk assessment) are specific and unambiguous.

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 provides explicit placement in a workflow: 'after backtest_strategy, before execution' and instructs to 'Check asset_classification first'. It also warns against exceeding the suggested_size_usd and references get_trading_workflow for broader context. This gives clear when-to-use and what-to-check-before-use guidance, fully differentiating it from related risk tools.

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