Skip to main content
Glama
Sign In
Polarion MCP Server

Polarion MCP Server

by phillipboesger
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Run Polarion job and wait

run_job_and_wait
Destructive

Submits a Polarion asynchronous job, polls until it reaches a terminal state or timeout, then returns job status and log tail for bounded job monitoring.

Instructions

Submits one Polarion asynchronous job, polls until a terminal state or timeout, then returns {jobId, status, state, message, logTail}. Provide the executeJob request body with a job factory ID and any factory-specific parameters; job semantics vary by factory. Requires permission to execute that job. Polling cancellation or timeout stops waiting but does not cancel the Polarion job; use executeJob and getJob separately when you do not need a bounded wait and log tail.

Input Schema

NameRequiredDescriptionDefault
dry_runNoReturn a preview without submitting the job.
requestBodyYesJSON body passed to `executeJob`; factory-specific parameters vary by jobId.
log_tail_charsNoMaximum returned log tail characters; defaults to 4000 and is capped at 20000.
max_wait_secondsNoMaximum time to poll; defaults to 120 seconds and is capped at 600.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv1.4.4
    • changedInput schema / properties / dry_run / description
      Previous value: -"Preview the job request without executing it."New value: +"Return a preview without submitting the job."
    • changedInput schema / properties / log_tail_chars / description
      Previous value: -"Maximum log tail length (default 4000, capped at 20000)."New value: +"Maximum returned log tail characters; defaults to 4000 and is capped at 20000."
    • changedInput schema / properties / max_wait_seconds / description
      Previous value: -"Maximum polling time; defaults to 120 seconds and is capped at 600."New value: +"Maximum time to poll; defaults to 120 seconds and is capped at 600."
    • changedInput schema / properties / requestBody / description
      Previous value: -"Parameters passed to executeJob."New value: +"JSON body passed to `executeJob`; factory-specific parameters vary by jobId."
    • addedInput schema / properties / requestBody / properties / jobId / description
      Added value: +"Polarion job factory ID, such as one listed by the server’s job catalog."
    • addedInput schema / properties / requestBody / properties / name / description
      Added value: +"Optional job name supplied to the selected factory."
    • addedInput schema / properties / requestBody / properties / nodeId / description
      Added value: +"Optional Polarion node ID when the selected factory requires a node scope."
    • addedInput schema / properties / requestBody / properties / params / description
      Added value: +"Optional factory-specific job parameters as a JSON object."
    • addedInput schema / properties / requestBody / properties / scope / description
      Added value: +"Optional scope value interpreted by the selected job factory."
  2. Addedv1.4.0

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing the key non-obvious behavior: polling cancellation or timeout stops waiting but does NOT cancel the Polarion job. That is a real semantic trap the destructiveHint/openWorldHint annotations cannot convey, and it adds the permission requirement and the factory-dependent variance in job semantics.

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 submit/poll/return cycle, then the input contract, then the safety caveat and sibling routing — a sensible order with dense sentences. Slightly crowded, but no sentence is filler.

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 a destructive, open-world, long-polling tool with a nested body and no output schema, it covers inputs, return fields, failure semantics of the wait, permissions, and alternatives. The only gap is what a non-terminal status means for the caller's next step (e.g. re-query via getJob), which would complete the picture.

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 coverage is 100%, so the baseline is 3, and the description usefully adds that requestBody is the executeJob body and that job semantics vary by factory — context the flat 'factory-specific parameters' schema text does not fully capture. It does not restate the log_tail_chars/max_wait_seconds caps, but those are already in the schema.

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?

Names a specific verb (submits, polls, returns) and resource (one Polarion asynchronous job), and enumerates the exact return shape. It explicitly contrasts itself with executeJob and getJob, so the agent can distinguish it from siblings 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 Guidelines5/5

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

Gives both a when-to-use (bounded wait plus log tail) and a when-not-to-use with the named alternatives ('use executeJob and getJob separately when you do not need a bounded wait and log tail'). It also states the permission prerequisite, which is the main gating condition for invoking it.

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

Deploy Server

Other Tools