Runs read-only strategy simulations from product facts and retrospective data to calculate primary channels, keep/drop lists, cold-start stages, scaling conditions, and risk controls.
只读策略推演：从产品事实包和复盘口径算出主渠道、保留清单、不做清单、冷启动五阶段、放大条件、风控映射。
| Name | Required | Description | Default |
|---|---|---|---|
| facts | Yes | 产品事实包（同 mkt gtm diagnose） | |
| retro_facts | No |
Changes observed during successful MCP inspections.
v0.13.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full load, and '只读' is a genuinely useful disclosure that this performs no writes. However, other behaviors an agent needs are absent: whether derivation is deterministic, whether absent optional input changes results, permission requirements, or failure modes when the facts pack is malformed.
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?
A single front-loaded sentence that leads with the read-only modality before enumerating outputs. No filler, though the six-item output list is dense and would read better separated from the modality clause.
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?
The enumeration of six output categories partly compensates for having no output schema, and the modality is stated. But for a nested-object, derivation-style tool with 50% schema coverage, the description omits input field expectations, behavior when optional input is missing, and any indication of output structure beyond a label list.
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 50%. The description clarifies that `facts` is a product facts pack and that `retro_facts` is the retro '口径' (measurement baseline), which adds meaning beyond the empty schema entry for retro_facts. It still does not explain what fields either nested object expects or what happens if retro_facts is omitted.
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 modality and verb ('只读策略推演') plus the exact artifacts computed (main channel, retention list, do-not-do list, cold-start stages, amplification conditions, risk-control mapping). This is far more specific than a name restatement, though it does not name a sibling it differs from (e.g., mkt_gtm_design or mkt_retro_analyze).
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?
No when-to-use or when-not-to-use guidance and no routing to alternatives among the many planning siblings (mkt_gtm_design, mkt_gtm_diagnose, mkt_channel_plan). The only usage hint is the parenthetical '同 mkt gtm diagnose' for input shape, which is about format, not invocation conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.