pb_forecastCalculates P50, P85, and P95 completion forecasts for a board, fix version, or epic to show likely finish dates and schedule risk.
P50/P85/P95 completion for a board, fix version or epic.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | board | |
| plan_id | Yes | ||
| scope_id | No |
| Name | Required | Description | Default |
|---|---|---|---|
| scope | Yes | ||
| primary | Yes | Completion dates for one forecast method. | |
| alternative | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds the useful fact that the result is percentile completion estimates rather than a single date, but says nothing about how percentiles are computed, how fresh the data is, or what happens when scope_id is omitted.
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?
Extremely short and front-loaded, but it is a bare noun phrase with no verb, and the terse wording forces the reader to decode 'P50/P85/P95 completion' and reconcile 'fix version' with the schema. Brevity here costs clarity rather than buying it.
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?
With 3 parameters at 0% schema coverage and a scope/scope_id dependency to convey, the description omits the essential calling contract. The existing output schema and annotations relieve it of return-value and safety duties, but the input semantics gap remains significant.
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%, and the description only loosely echoes the scope enum (saying 'fix version' where the enum says 'milestone'). It never explains what plan_id identifies or that scope_id must be a board/milestone/epic id matching scope, so the most error-prone parameters are undocumented everywhere.
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 the concrete output (P50/P85/P95 completion estimates) and the scopes it covers, which is specific enough to separate it from pb_plan_summary or pb_critical_path. It stops short of saying whether the percentiles are dates or effort, and 'fix version' conflicts with the schema's 'milestone' enum value.
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?
No guidance on when to pick this over siblings like pb_plan_summary, pb_critical_path, or pb_flow_metrics, and no prerequisites (e.g., that plan_id must reference an existing plan). The agent must infer selection criteria from tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.