Skip to main content
Glama
CKBrennan

overtone-news-mcp

pulse

Detect spikes in emotional tones (angry, sad, fearful) by polling. Returns spike ratio and alerts when spike ratio exceeds 1.5 with meaningful volume.

Instructions

Pollable spike detector. Returns spike_ratio and a boolean spiking for each watched tone (default angry/sad/fearful), plus an alerts array populated when spike_ratio >= 1.5 with meaningful volume. Intended for repeated polling (every 5-15 min). Only surface to the user when alerts is non-empty.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
tonesNo
recent_hoursNo
baseline_hoursNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Pulse tool handler: a pollable spike detector that calls the 'pulse' API endpoint. Accepts query, optional tones filter, recent_hours (1-168), and baseline_hours (1-720). Returns spike_ratio, spiking flags per tone, and alerts when spike_ratio >= 1.5.
    @mcp.tool()
    def pulse(
        query: Query,
        tones: Annotated[list[ToneName], Field(max_length=7)] | None = None,
        recent_hours: Annotated[int, Field(ge=1, le=168)] = 6,
        baseline_hours: Annotated[int, Field(ge=1, le=720)] = 72,
    ) -> dict[str, Any]:
        """Pollable spike detector. Returns spike_ratio and a boolean
        `spiking` for each watched tone (default angry/sad/fearful), plus
        an `alerts` array populated when spike_ratio >= 1.5 with meaningful
        volume. Intended for repeated polling (every 5-15 min). Only
        surface to the user when `alerts` is non-empty."""
        body: dict[str, Any] = {
            "query": query,
            "recent_hours": recent_hours,
            "baseline_hours": baseline_hours,
        }
        if tones:
            body["tones"] = tones
        return _post("pulse", body)
  • Schema types used by pulse: Query (str, 1-500 chars), ToneName (literal list of 7 emotions), and Bin type.
    Query = Annotated[str, Field(min_length=1, max_length=500)]
    ToneFilter = Literal["positive", "negative", "informational"]
    ToneName = Literal[
        "happy", "funny", "hopeful", "informational", "angry", "sad", "fearful"
    ]
    Bin = Literal["hour", "6h", "day"]
  • Registration of 'pulse' as an MCP tool via the @mcp.tool() decorator on the FastMCP instance.
    @mcp.tool()
  • Helper function _post that sends HTTP POST requests to the Overtone API with the API key. Used by pulse to call the 'pulse' endpoint.
    def _post(path: str, body: dict[str, Any]) -> dict[str, Any]:
        with httpx.Client(timeout=HTTP_TIMEOUT) as client:
            resp = client.post(
                f"{API_URL}/{path}",
                headers={"X-API-Key": _load_api_key()},
                json=body,
            )
            resp.raise_for_status()
            return resp.json()
Behavior2/5

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

With no annotations, the description must disclose behavioral traits. It implies read-only polling but does not address mutation, permissions, rate limits, or side effects. The lack of such detail is a significant gap for a tool without annotations.

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?

The description is three front-loaded sentences with no wasted words. Every sentence adds value: defines output, polling frequency, and UI guideline.

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?

Despite having an output schema, the description omits crucial parameter roles and behavioral details. For a tool with 4 parameters and no annotations, this is incomplete guidance for correct invocation.

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 0%; the description only mentions default tones but leaves out the purpose of 'query', 'recent_hours', and 'baseline_hours'. This insufficiently compensates for the schema's lack of 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 clearly states it is a 'Pollable spike detector' and lists specific outputs (spike_ratio, boolean spiking, alerts), distinguishing it from sibling tools like emerging, news, report, etc. The purpose is unambiguous.

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?

Explicitly states intended polling frequency (every 5-15 min) and when to surface alerts (only when non-empty). Does not explicitly contrast with siblings but provides clear context for appropriate 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/CKBrennan/overtone-news-mcp'

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