Check a task’s current state, changed files, and evidence, or list active tasks by omitting the task ID. Use it to review progress before continuing work.
See what a task changed so far: state, files, evidence. Omit task_id → list active tasks.
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | No | Task id; omit = list. | |
| workspace_dir | Yes | Project root (abs). |
Changes observed during successful MCP inspections.
v0.5.28Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It discloses the shape of the returned payload (state, files, evidence) and the listing fallback behavior, which implies a read-only inspection, but it never states that explicitly, nor any permission or scope requirements. Useful but incomplete for a zero-annotation tool.
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 compact clauses, the primary purpose front-loaded and the mode switch second. Every fragment carries information; nothing is padded.
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 simple 2-parameter tool with full schema coverage and no output schema, the description says what is reported and how to get a list instead of a single task. The main remaining gap is not saying what 'active' means or what happens when a task_id is unknown.
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%: task_id already says 'omit = list' and workspace_dir says 'Project root (abs).' The description restates the omit-to-list behavior and adds 'active' as a qualifier on the listing, but adds no real semantics about what a task_id accepts or what workspace_dir scoping means. Baseline 3 is appropriate.
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?
Specific verb and resource: reports what a task changed so far, naming the returned facets (state, files, evidence). It also covers the dual mode (single task vs. list). It does not distinguish itself from siblings like code_audit, code_query, or code_check, so it stops short of a 5.
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?
'Omit task_id → list active tasks' gives explicit mode-selection guidance, which is genuinely useful. However there is no guidance on when to prefer this over sibling status/audit tools (code_audit, code_query, code_check) and no stated exclusions, leaving usage implied rather than specified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.