Retrieve the current iteration from PLAN.md to know what to work on now without reading the entire file.
JSON for the current iteration (what to work on now). Preferred agent entry — avoids reading all of PLAN.md.
| Name | Required | Description | Default |
|---|---|---|---|
| plan_path | No | Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md. |
Changes observed during successful MCP inspections.
v0.7.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden. It reveals that the tool returns JSON and is efficient because it avoids reading all of PLAN.md, which is useful. But it does not mention error conditions, what happens if no PLAN.md exists, or any side-effect profile, though the read-only nature is strongly implied.
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?
The description is two short clauses with no wasted words. It front-loads the core output and then provides the usage rationale, exactly the kind of compact, efficient definition that helps an agent.
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 tool with one optional parameter and no output schema, the description is nearly complete: it states the return type (JSON), the target (current iteration), and when to prefer it. It lacks explicit error behavior and sibling differentiation, but neither is likely to block correct invocation in the normal 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?
The schema already documents plan_path with 100% coverage, including its optionality and default behavior. The description does not add parameter-specific details, so it neither helps nor hurts; the baseline of 3 applies.
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 description clearly states what the tool does: returns JSON for the current iteration, with the parenthetical clarifying 'what to work on now.' It is specific about the verb and resource, and the mention of being the 'preferred agent entry' offers some distinction, but it does not explicitly differentiate from sibling tools like get_iteration or show_current_iteration.
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?
The description gives clear context for when to use it: it is the 'preferred agent entry' and avoids reading all of PLAN.md, implying the main alternative is manually reading the file. However, it does not explicitly state when to prefer other tools or provide exclusions, so it falls short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.