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

Beyond annotations (readOnlyHint=false, destructiveHint=true), the description adds substantial operational context: it is a write operation requiring confirmation, external calls execute directly under the apikey identity, only one concurrent run per user is allowed, and it gives a full pricing formula (base 5 + 10/1k bars with 5/1k above 10k bars + 1/1k tokens). This is exactly the kind of cost and authorization detail annotations cannot convey.

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?

Despite being a single dense sentence block, everything is front-loaded: the action and write/confirm warning come first, then mode routing, then concurrency, then cost. No sentence is filler; the parenthetical cost formula is compact and relevant for an agent deciding whether to invoke.

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 an 11-parameter tool with no required fields, nested objects (thresholds), and no output schema, the description covers mode selection, cost, concurrency, and execution identity well. It stops short of saying what a successful run returns (run id, async vs sync), which would help an agent chain into platform_factory_runs.

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 description coverage is already 100%, so the baseline is 3. The description goes beyond the schema by mapping sourceType values to the parameters they require (optimize needs strategyId, llm uses intent/nCandidates, search uses factorIds), which is meaningful cross-parameter semantics the per-field descriptions do not state.

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 gives a specific verb and resource ('发起策略工厂运行') and immediately enumerates the three run modes (llm for description generation, search for condition scanning, optimize for existing strategies), which lets an agent distinguish this from the sibling list tool platform_factory_runs. It never names a sibling explicitly, so identification relies on the verb 'initiate' versus 'list'.

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?

Usage guidance is embedded per mode: sourceType=llm for description generation, search for condition scanning, optimize for optimizing an existing strategy and that mode requires strategyId. It also states the concurrency constraint that only one run per user is allowed at a time. What is missing is explicit when-not-to-use guidance or a pointer to platform_factory_runs for checking existing runs.

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