huly-mcp-selfhost

finish_work

Close out an issue by posting a summary comment, linking the pull request, and moving the status to review.

Instructions

Hand back: summary comment, link PR, status to review

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "workspace": "<workspace>",
      "identifier": "<identifier>",
      "summary": "<summary>"
    },
    "name": "finish_work"
  }
}

Input Schema

Name	Required	Description	Default
`summary`	Yes	Markdown
`workspace`	Yes
`identifier`	Yes	Issue id
`statusName`	No	null keeps status	Review in progress
`pullRequest`	No	#12, URL or Huly id

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.5.1Nov 12, 2026

TDQS

C2.8/5.0

Behavior3/5

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

Annotations supply only destructiveHint=false, so the description carries most of the burden. It does disclose the three side effects (comment, PR link, status change), which is the core behavioral information, but says nothing about notifications to watchers, reversibility, permission needs, or whether the comment is mandatory.

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?

Ten words, front-loaded, with zero filler. It is efficient, though the terseness edges into under-specification that other dimensions penalize.

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

Completeness2/5

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

This is a multi-parameter mutation with no output schema and weak annotations, yet the description never explains defaults, what happens when optional fields are omitted, what the call returns, or how it completes the workflow started by start_work. For this complexity, it does too little.

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 80%, so the baseline is 3. The description's 'link PR' and 'status to review' loosely map to pullRequest and statusName, but it adds no syntax or format detail (e.g., acceptable PR references, null-keeps-status behavior) beyond what the schema already documents.

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

Purpose3/5

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

The fragment 'Hand back: summary comment, link PR, status to review' does enumerate the three actions performed, so the resource is inferable (a work item being handed off). But it is written as terse shorthand rather than a verb+resource statement, and it never names its obvious counterpart start_work, leaving the agent to infer the pairing.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no prerequisite or exclusion, and no mention of start_work or any alternative for closing out work. The agent must guess that this is the terminal step of an issue workflow.

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

Deploy Server