Rillsoft Project MCP server

Official

Overview Schema Source Related Servers Discussions Admin

Split task

rillsoft_task_split

Split a project task at a chosen time, at its progress point, or into proportional parts by percent, effort, duration, cost, or deliverable.

Instructions

Splits a task. Give exactly one of splitTime, completedPart or proportions. Splitting into n parts is a single undo step. The result is parts[] carrying uuid, wbs, number, name, start, finish, durationHours and progressPercent in WBS order. Beware: every part keeps the UUID of the original task, which is what preserves the baseline reference. What is unique is the number; passed as number it addresses one part in rillsoft_task_update, rillsoft_task_split and rillsoft_task_split_options_get. The name stays the same for all parts as well (just as in the user interface); rename them one by one through rillsoft_task_update.

Input Schema

TableJSON Schema

Name	Required	Description
`uuid`	Yes	UUID of the task
`number`	No	narrows an ambiguous UUID down to one part; required to split an already split task again
`sameRow`	No	draw the parts on one display row (defaults to true); only together with proportions
`linkParts`	No	create a finish_start dependency between the parts (defaults to true); only together with proportions
`splitTime`	No	split point, DD.MM.YYYY hh:mm, and it has to lie inside the task; this covers both a starting shift and a conflict point
`proportions`	No	split by criterion: { criterion: percent\|deliverable\|effort\|duration\|cost, values: [ ... ] }. The values are given in the metric of the criterion (rillsoft_task_split_options_get reports metric and totalValue); whatever remains is appended where it can carry a part
`completedPart`	No	true = split at the point of progress; the only way permitted once times have been recorded

Output Schema

TableJSON Schema

Name	Required	Description	Default
`count`	Yes	number of parts
`parts`	Yes	the parts in WBS order; all carry the UUID of the original task

Schema Changelog

Changes observed during successful MCP inspections.

First observedv10.0.626Oct 17, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) by disclosing that a multi-part split is a single undo step, that every part retains the original UUID to preserve the baseline reference, that only 'number' is unique, and that names stay identical for all parts. These are exactly the non-obvious behaviors an agent needs and are consistent with the annotations.

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

Conciseness4/5

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

Front-loaded with the action and the required-argument constraint, then layers in behavioral caveats. Dense but every sentence carries distinct information (undo granularity, UUID preservation, naming). Slightly long, with the UUID/name explanation spanning multiple sentences that could be tightened.

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?

Output schema exists, so return-value explanation is not strictly required, yet the description still says the result is parts[] in WBS order. For a non-idempotent mutation with many interacting parameters, this is close to complete; only permission/authorization prerequisites are unaddressed.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description nevertheless adds cross-tool semantics the schema cannot convey: 'number' addresses one part across rillsoft_task_update, rillsoft_task_split and rillsoft_task_split_options_get, and explains why names must be renamed one by one. This is genuinely beyond the property descriptions.

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

Purpose5/5

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

The opening sentence 'Splits a task' gives a specific verb and resource, then immediately constrains the operation with the exactly-one-of rule over splitTime, completedPart or proportions. It is distinguishable from siblings like rillsoft_task_update (rename) and rillsoft_task_split_options_get (options) without opening any schema.

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?

States the mutual-exclusion constraint ('Give exactly one of...') and a hard pre-condition ('completedPart ... the only way permitted once times have been recorded'). It also routes the agent to rillsoft_task_update for renaming and rillsoft_task_split_options_get for options. No explicit when-not-to-use this tool at all, but the context is clear.

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

Deploy Server