Polarion MCP

Overview Schema Source Related Servers Discussions Admin

list_work_item_links

Read-only

Retrieve a work item's links for forward or backward direction. Forward links include role and suspect status; backward links omit role.

Instructions

List a work item's links, one direction per call.

Forward carries role (parent, verifies, …) and suspect; back is a Lucene fallback that drops role (always None) — recover it via forward on the source.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`direction`	No		forward
`page_size`	No
`project_id`	Yes	Polarion project ID.
`page_number`	No
`work_item_id`	Yes	Work item ID (e.g. 'MCPT-001').

Output Schema

TableJSON Schema

Name	Required	Description	Default
`page`	Yes
`items`	Yes
`has_more`	No
`page_size`	Yes
`total_count`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2.0.0Jul 22, 2026
Removedv2.0.0Jul 22, 2026
Changed1 schema field changedv1.4.0Jun 26, 2026
- changedInput schema / properties / work_item_id / description
```
Previous value: -"Work Item ID (e.g. 'MCPT-001')."New value: +"Work item ID (e.g. 'MCPT-001')."
```

Changed14 schema fields changedv1.1.0Jun 9, 2026

removedInput schema / properties / direction / description

Removed value: -"'forward' (outgoing) or 'back' (incoming); call twice if both needed."

removedInput schema / properties / page_number / description

Removed value: -"Page number to retrieve (1-based, default 1)."

removedInput schema / properties / page_size / description

Removed value: -"Number of links per page (1-100, default 100)."

removedOutput schema / properties / has_more / description
```
Removed value: -"True if more pages follow."
```

changedOutput schema / properties / items / items / description

Previous value: -"A work item link with the target's summary metadata.\n\n``direction='forward'`` is an outgoing link (this work item links to\nthe target); ``'back'`` is an incoming link (the target links to this\nwork item). The back-direction Lucene fallback does not expose the\noriginating role, so ``role`` is ``None`` for every back-direction\nitem. ``suspect`` marks links whose target changed since the link\nwas last reviewed; it is only meaningful in the forward direction."New value: +"A work item link with the target's summary metadata."

removedOutput schema / properties / items / items / properties / direction / description
```
Removed value: -"'forward' for outgoing links, 'back' for incoming."
```
removedOutput schema / properties / items / items / properties / document_name / description
```
Removed value: -"Linked item's document name; empty when not module-bound."
```
removedOutput schema / properties / items / items / properties / id / description
```
Removed value: -"Linked Work Item ID (e.g. 'MCPT-002')."
```
removedOutput schema / properties / items / items / properties / role / description
```
Removed value: -"Link role (e.g. 'parent'); None on back-direction links."
```
removedOutput schema / properties / items / items / properties / space_id / description
```
Removed value: -"Linked item's document space; empty when not module-bound."
```
removedOutput schema / properties / items / items / properties / status / description
```
Removed value: -"Linked work item workflow status; empty when unreported."
```
removedOutput schema / properties / items / items / properties / suspect / description
```
Removed value: -"True when the link is marked as suspect."
```
removedOutput schema / properties / items / items / properties / title / description
```
Removed value: -"Linked Work Item title."
```
removedOutput schema / properties / items / items / properties / type / description
```
Removed value: -"Linked work item type; empty when unreported."
```

First observedv0.9.0May 28, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations declare readOnlyHint=true, which the description aligns with by describing a read operation. The description adds behavioral context: direction impacts returned data (role preservation). No contradictions. Could elaborate on pagination behavior.

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?

Two sentences, highly concise and front-loaded. No redundant phrasing. Every sentence adds value.

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?

Given read-only annotations, output schema presence, and the tool's listing nature, the description covers the key nuance (direction behavior). Pagination and other parameters are not addressed, but output schema likely covers return structure. Slightly incomplete.

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

Parameters2/5

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

Schema description coverage is 40%, only 2 of 5 parameters are described in schema. The description adds no parameter-level details (e.g., syntax, constraints). The direction enum is implied but not explained further. Additional parameter context would improve score.

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 description clearly states the tool lists a work item's links, with a specific verb ('List') and resource ('work item's links'). It also notes directionality, distinguishing it from potential siblings like delete or update link tools.

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?

The description explains when to use forward vs back: forward carries role and suspect; back is a Lucene fallback that drops role. It provides a recovery suggestion ('recover it via forward on the source'). However, it lacks explicit alternatives or when-not-to-use scenarios.

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

Deploy Server