Skip to main content
Glama

get_team_pulse

Read-onlyIdempotent

Summarize a board's recent shipped work and upcoming items within set windows, with velocity-based insight flags and per-developer balance to highlight risks like backlog growth or overload.

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
Install Server

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds substantial context beyond those: how columns are classified, what data is fetched, the visibility limitation for unmapped state values, and the heuristic flags. No contradiction with annotations.

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 long but well-structured with a summary, scope section, flags, and arguments. Each section earns its place, though a few phrases could be tightened (e.g., repeating 'by design' clarifications). Slight over-explanation but not enough to lose a point.

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?

Covers purpose, behavior, scope, parameters, output format, and edge cases. An output schema exists, and the description mentions the JSON payload structure but doesn't need to enumerate it. Nothing essential is missing for an agent to invoke this tool correctly.

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?

Schema description coverage is 0%, so the description carries the full burden. It explains every parameter with defaults, purpose, and justification (e.g., max_idle_days with measured noise data, format options). This fully compensates for the lack of schema descriptions.

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 states a specific verb and resource: 'Team pulse for a board' with what it returns (shipped, upcoming, insights). It clearly distinguishes itself from sibling tools like search_issues and get_team_dashboard by scoping to board columns and mentioning alternatives.

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?

Explicit when-to-use guidance is provided, including a 'Scope' section that warns about unmapped states and explicitly recommends 'search_issues' for full project scans. This is a clear directive on when this tool is appropriate and when it is not.

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

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