Rillsoft Project MCP server

Official

by rillsoft

Overview Schema Source Related Servers Discussions Admin

JavaScript

Local

Create dependency

rillsoft_task_dependency_create

Idempotent

Creates a task dependency between two existing tasks, so Rillsoft Project recalculates dates from the link. Use it to define predecessor-successor relationships without creating or moving tasks.

Instructions

Creates a dependency between two tasks. It links existing tasks; it does not create them, and it does not move them - RP computes the new dates from the link. Removing it again goes through rillsoft_task_dependency_delete. In a portfolio, as in the user interface: across the project boundary a file portfolio refuses the dependency; a portfolio of the Integration Server creates it on the server as a RIS link (finish-start, start-start, finish-finish or start-finish with an absolute lag). One undo step.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`type`	No	finish_start is the default: the successor begins once the predecessor is done, and a distance in between is allowed. Use finish_start_no_delay only where the successor has to follow immediately with no delay at all. Besides those: start_start (both begin together), finish_finish (both end together) and start_finish (the successor ends when the predecessor begins)	finish_start
`successorUuid`	Yes	UUID of the successor
`predecessorUuid`	Yes	UUID of the predecessor
`dependencyDistanceType`	No	absolute (the default) counts plain time, calendar counts calendar time, relative counts a share of the task duration	absolute
`dependencyDistanceHours`	No	distance in hours (with dependencyDistanceType absolute or calendar) respectively a share (relative)

Output Schema

TableJSON Schema

Name	Required	Description
`type`	Yes	kind of the created dependency; finish_start is the default
`successorUuid`	Yes	UUID of the successor
`predecessorUuid`	Yes	UUID of the predecessor

Schema Changelog

Changes observed during successful MCP inspections.

First observedv10.0.626Oct 17, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already declare readOnly=false, idempotent=true, destructive=false, and the description enriches this with genuine behavioral context: RP recomputes dates from the link, file portfolios refuse cross-project dependencies while an Integration Server portfolio creates a RIS link, and the change consumes one undo step. The refusal/failure condition and undo semantics are exactly what annotations cannot convey.

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-loads the core action and the negative scoping ('does not create them, does not move them') before the more complex portfolio paragraph. The portfolio sentence is dense and multi-clause but every element carries information; slightly long but not wasteful.

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

Completeness5/5

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

For a write tool with an output schema (so return values needn't be explained) and annotations covering the safety profile, the description closes the remaining gaps: side effects on dates, portfolio-dependent behavior, failure conditions, and undo. An agent has everything needed to invoke it correctly.

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 coverage is 100%, so all five parameters, both enums, and the distance semantics are already fully documented in the schema. The description echoes the dependency types and lag concept but adds no syntax or format detail beyond what the schema provides, so the baseline 3 is appropriate.

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?

States a specific verb and resource ('Creates a dependency between two tasks') and immediately draws the boundary against sibling task_create by clarifying it links existing tasks rather than creating or moving them. An agent can distinguish this from task_create and task_dependency_delete 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?

Gives clear context on when this applies (linking existing tasks, date recomputation by RP) and names the removal path (rillsoft_task_dependency_delete). It lacks an explicit when-not or alternative-routing statement beyond the create/delete contrast, but the intended use case is unambiguous.

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

Deploy Server