Skip to main content
Glama
velesnitski

yt-mcp

by velesnitski

get_team_pulse

Retrieve shipped and upcoming work for a board, with velocity-aware insights and flags to identify blockages, WIP overload, and other team health signals.

Instructions

Team pulse for a board: what shipped in the last {lookback_days}d and what's coming in the next {horizon_days}d, with velocity-aware insight flags and a team-balanced per-dev view.

Reads the board's column structure, classifies columns by role (triaged/incoming/re_entry/in_progress/done), then fetches:

  • Lookback: closed, released, reopened, new incoming

  • Forward: ready-to-pull, pipeline-unblockers, recent incoming

Scope: project + board-column-scoped. Issues are queried by project: <PROJ> State: {<board state>, ...} — so any State enum value on the project that the board does NOT render as a column is invisible. Newly-created tickets in unmapped states won't surface until they're moved to a state that has a column. This is by design (the board defines what "matters" for the team's workflow) but can surprise consumers expecting a full project scan — use search_issues with a project filter if you want everything.

Heuristic flags surface "should I act?" signals: backlog growth, reopen rate, WIP overload (concurrent dev work), pipeline overload (downstream-of-dev clog), bottlenecks, deadline cliff, stale queue.

Args: board_name: Board name (partial match), ID, or URL. horizon_days: Forward planning window (default 14). lookback_days: Backward velocity window (default 30 — smooths weekly variance). limit: Max items per section (default 10). format: "report" (default, markdown) or "json" (JSON-stringified payload for programmatic consumption — board, metrics, pipeline_counts, ranked section lists, team_balanced, insights). max_idle_days: Drop pipeline + re_entry items not updated within this many days (default 60). Pass 0 to disable. Justified by real-data measurement showing 50%+ noise from abandoned tickets that still technically sit in In Progress/For review states. max_overdue_days: Drop forward items whose deadline is past by more than this many days (default 30). Pass 0 to disable. Deeply overdue items need a different conversation than "next up". instance: YouTrack instance (optional).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
formatNoreport
instanceNo
board_nameYes
horizon_daysNo
lookback_daysNo
max_idle_daysNo
max_overdue_daysNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

With no annotations, the description fully shoulders transparency. It details the scoping to board columns, the invisibility of unmapped states, heuristic flags, and parameter rationales like filtering idle/overdue items. It warns consumers about potential surprises, demonstrating high behavioral transparency.

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?

The description is well-structured with a clear opening, scoping note, feature list, and parameter breakdown. While lengthy, every section adds value for a complex tool. Minor redundancy exists but does not detract significantly.

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?

The description covers all key aspects: purpose, scope, parameters, behavior, and output format. It references an output schema and provides sufficient context for decision-making. Missing explicit mention of error handling or authentication, but overall complete given the tool's complexity.

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

Parameters5/5

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

Despite 0% schema description coverage, the description provides thorough explanations for all 8 parameters, including defaults, use cases, and even justifications (e.g., 'max_idle_days' rationale for reducing noise). This richly compensates for the schema gap.

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 provides a 'team pulse for a board' focusing on shipped and upcoming items, with velocity insights. It distinguishes itself from siblings like 'search_issues' by explicitly noting its board-scoped nature and contrasting with full project scans.

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?

The description explicitly advises when not to use this tool (when a full project scan is needed) and suggests 'search_issues' as an alternative. It also clarifies the board-scoped limitation and provides guidance on format options for programmatic use.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/velesnitski/yt-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server