Identify stalled tasks still in non-terminal columns with no writes past a threshold and return idle seconds, helping agents report interruptions instead of mislabeling long-running work.
列出疑似停滞的任务：仍在非终态列、且超过阈值秒数没有任何写入。语义是「上报中断」而非「进度值没变」 —— 所以长任务必须周期性调用 update_progress 上报，否则会被误标。返回里带 idle_sec（静默了多久）。
| Name | Required | Description | Default |
|---|---|---|---|
| now | No | 参照时间（ISO8601），便于测试与回放；省略用当前时间 | |
| threshold_sec | No | 静默多少秒算停滞，默认 90 |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it delivers the key behavioral trait: the semantics is 'reporting interruption' rather than 'progress unchanged', plus the false-positive risk and the idle_sec return field. It omits auth/permission or pagination behavior, but the critical misinterpretation hazard is disclosed.
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?
Three sentences, front-loaded with the definition, then the semantic caveat, then the return field. The bolded warning is placed where it matters and no sentence is redundant.
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 zero-required-param read tool with no output schema, the description covers what the filter means and surfaces the one return field that matters (idle_sec). Nothing essential to calling it correctly is missing, though return shape beyond idle_sec is unspecified.
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 100%, so both parameters (now, threshold_sec) are already documented in the schema. The description reinforces the threshold concept and mentions idle_sec but adds no syntax or format detail beyond the schema, matching the baseline 3.
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+resource (列出疑似停滞的任务) and immediately operationalizes it: tasks still in non-terminal columns with no writes beyond the threshold. This is clearly distinguishable from sibling list_tasks, which has no such filter.
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 the triggering condition and warns that long tasks must periodically call update_progress or be mislabeled, which effectively names the corrective sibling action. It stops short of explicitly contrasting with list_tasks/list_events as alternatives, so it is strong context rather than full when/when-not routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.