forecast-mcp

Forecast delivery date from throughput (Monte Carlo)

forecast_completion

Read-onlyIdempotent

Forecast how many periods and calendar dates are needed to clear a backlog from historical throughput samples, returning P50/P80/P90/P95 estimates.

Instructions

Answer 'when will it be done?' from historical throughput instead of per-task estimates. Give the number of items completed in each recent period (e.g. stories per sprint) and the remaining backlog; the tool bootstraps future periods to forecast how many periods are needed to clear the backlog. Returns P50/P80/P90/P95 in periods, and calendar dates when a start date and period length are supplied. Optionally model scope creep with splitRate.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`seed`	No	PRNG seed. Fixed by default so results are reproducible; change it to explore alternate random streams.
`backlog`	Yes	Number of remaining items to complete (or the low end of a range).
`splitRate`	No	Scope-creep factor: expected new items created per completed item (0 = fixed scope, 0.1 = 10% growth).
`startDate`	No	Optional ISO start date (YYYY-MM-DD) to translate periods into calendar dates.
`iterations`	No	Number of Monte Carlo iterations (100..200000).
`periodDays`	No	Calendar days per period, used with startDate to compute completion dates.
`backlogHigh`	No	Optional high end of the backlog range. If set, backlog is sampled uniformly between `backlog` and `backlogHigh` (models scope uncertainty).
`periodLabel`	No	Label for one throughput period (e.g. sprint, week).	period
`distribution`	No	Probability distribution for the estimate. 'pert' (beta-PERT) is the project-management default.	pert
`targetPeriods`	No	Optional target number of periods. Returns the probability of finishing within it.
`throughputSamples`	Yes	Historical items completed per period (e.g. [5, 8, 3, 6, 7]). Sampled with replacement to model future periods.

Output Schema

TableJSON Schema

Name	Required	Description
`max`	Yes
`min`	Yes
`mean`	Yes
`seed`	Yes
`stdDev`	Yes
`histogram`	Yes
`iterations`	Yes
`percentiles`	Yes
`periodLabel`	Yes
`targetPeriods`	No
`completionDates`	No
`scopeCreepCapped`	Yes	True if any run hit the internal period cap (usually runaway scope creep).
`probabilityWithinTarget`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 27, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/closed-world, so the safety profile is covered. The description adds real behavioral value: it discloses the bootstrap mechanism, the percentile outputs (P50/P80/P90/P95) and the condition under which calendar dates appear, plus the optional splitRate scope-creep modeling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the question it answers, then mechanism, then outputs, then the optional parameter. No filler and each sentence carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter tool with a full output schema, the description covers the core mental model (inputs, bootstrap, outputs, scope creep) adequately. It omits discussion of distribution choices and iteration counts, but those are fully specified in the schema and annotations already cover safety.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter is already documented in the schema. The description only gestures at throughputSamples, backlog, and splitRate at a conceptual level, adding no syntax or format detail beyond the schema; baseline 3 is correct.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('forecast how many periods are needed to clear the backlog') and frames the exact question it answers ('when will it be done?'). It distinguishes itself from estimate-based siblings by contrasting 'historical throughput instead of per-task estimates', though it does not name forecast_duration/pert_estimate explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Specifies the required inputs (throughput per recent period + remaining backlog) that select this tool over per-task estimate approaches, and notes the optional start date/period length that unlocks calendar output. No explicit when-not or named alternative, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server