Read the task board's change log to see who moved which task between columns and when. Use since_seq for incremental pulls or task_id to view one task's full history.
读取变更流水（谁在什么时候把什么从哪列移到哪列）。since_seq 支持增量拉取；给定 task_id 可看单个任务的完整历史。
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 最多返回条数，默认 100 | |
| task_id | No | 只看该任务的历史 | |
| since_seq | No | 只返回 seq 大于此值的事件 |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. '读取' (read) and the described event payload make the read-only, non-destructive nature reasonably inferable, but nothing is said about auth requirements, ordering, retention, or rate limits for polling.
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?
Two tight sentences: purpose first, then the two parameter-driven modes. No filler, nothing repeated from the schema, and the most important information leads.
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 read-only, zero-required-parameter list tool with no output schema, the description is nearly sufficient. It omits ordering of events and how limit interacts with since_seq across a long history, which are minor but real gaps for a polling use case.
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, but the description adds intent beyond the raw field docs: since_seq is framed as an incremental-sync cursor and task_id as a per-task history filter. That tells an agent how to combine them, not just what they accept.
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 verb and resource (read the change/event stream) and even spells out the returned content: who moved what from which column to which column, when. That distinguishes it from list_tasks or board_snapshot without naming them, though it stops short of explicit sibling differentiation.
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?
Explains two concrete usage modes: incremental pulling via since_seq and full single-task history via task_id. This is clear operational context, but it never states when to prefer this tool over alternatives like board_snapshot or list_tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.