Generate a read-only sprint plan from facts and goals, including parallel N-day workflows, hourly schedules, daily targets, capacity checks, and red lines.
只读冲刺方案：目标方案→N 天并行工作流、小时级排期、每日目标、加速杠杆、容量校验与红线。
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| goal | Yes | ||
| facts | Yes | ||
| start | No | ||
| target | No | ||
| platforms | No | ||
| secondary | No | ||
| launch_hour | No | ||
| hours_per_day | No |
Changes observed during successful MCP inspections.
v0.13.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It usefully discloses that the operation is read-only and that the result includes capacity validation and red lines, but it says nothing about permission requirements, failure behavior, or how the nested facts input is validated. For a 9-parameter composite planner this is a thin disclosure.
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 dense sentence that front-loads the read-only guarantee and then enumerates the outputs. Nothing is padded, though the enumeration of output artifacts would read better as a short structured list.
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 tool has 9 parameters, a nested object, no annotations and no output schema, yet the description is one sentence naming outputs only. An agent can form a rough idea of what it gets back but has almost no basis for constructing a valid call, especially the required facts payload.
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 0% across 9 parameters, including a nested facts object, so the description must compensate and largely does not. It hints at days ('N 天') and hour-level fields, but never explains what facts should contain, what target or secondary mean, or how platforms interacts with the plan. Required facts and goal get no guidance at all.
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 definition states a specific resource (a sprint plan) with its key output components: N-day parallel workflows, hourly scheduling, daily targets, acceleration levers, capacity checks and red lines. That is far more informative than the bare name. However, it never distinguishes itself from nearby planning siblings such as mkt_goal_plan, mkt_cadence or mkt_workflow, so an agent cannot tell why it should pick this planner over those.
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?
There is no statement of when to use this tool, when not to, or which sibling to prefer for adjacent planning tasks. The only usable signal is the implicit 'read-only' framing, which does not tell an agent when sprint planning is the right move versus goal planning or cadence work.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.