Skip to main content
Glama
CKBrennan

overtone-news-mcp

news

Retrieve news articles on any topic, each tagged with tone and brand-safety signals. Use for analyzing current events or topic coverage.

Instructions

Retrieve news articles about a topic, each tagged with tone and brand-safety signals. Returns up to max_results articles from the last days days. Use for any question about current events or a topic's coverage. Include request_id from the response when you later call report to log which articles you actually showed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
max_resultsNo
daysNo
tone_filterNo
brand_safe_onlyNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The @mcp.tool() decorated function 'news' that executes the tool logic: takes query, max_results, days, tone_filter, and brand_safe_only; builds the request body; and sends it to the /news API endpoint.
    @mcp.tool()
    def news(
        query: Query,
        max_results: Annotated[int, Field(ge=1, le=20)] = 15,
        days: Annotated[int, Field(ge=1, le=10)] = 3,
        tone_filter: ToneFilter | None = None,
        brand_safe_only: bool = True,
    ) -> dict[str, Any]:
        """Retrieve news articles about a topic, each tagged with tone and
        brand-safety signals. Returns up to `max_results` articles from the
        last `days` days. Use for any question about current events or a
        topic's coverage. Include `request_id` from the response when you
        later call `report` to log which articles you actually showed."""
        body: dict[str, Any] = {
            "query": query,
            "max_results": max_results,
            "days": days,
            "brand_safe_only": brand_safe_only,
        }
        if tone_filter:
            body["tone_filter"] = tone_filter
        return _post("news", body)
  • Type aliases used as schemas for tool parameters, including Query (min 1, max 500 chars), ToneFilter, ToneName, and Bin which are all used by the 'news' tool and other tools.
    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"]
  • The @mcp.tool() decorator that registers the 'news' function as an MCP tool on the FastMCP server instance.
    @mcp.tool()
  • The _post helper function is called by the 'news' tool (as _post('news', body)) to send the HTTP POST request to the Overtone API with the API key header.
    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()
Behavior3/5

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

No annotations are provided, so the description must fully disclose behavior. It explains data returned (articles with tone and brand-safety signals) and the presence of `request_id`, but does not mention authorization, rate limits, or read-only nature. Adequate but not comprehensive.

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?

Four sentences, front-loaded with the core purpose, no redundant words, and each sentence adds value: purpose, parameters, usage context, and follow-up instruction.

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?

Given the output schema exists, the description does not need to detail return format. It covers the main functionality, parameters, and the workflow linked to `report`. Minor omissions like the required `query` field and defaults are not critical but would improve completeness.

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?

With 0% schema description coverage, the description adds significant meaning: it explains `max_results` and `days` explicitly, and implies the purpose of `query` (topic) and the tags (tone and brand-safety signals) which relate to `tone_filter` and `brand_safe_only`. It does not explain default values or allowed enums, but compensates well.

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 action ('Retrieve news articles') and the resource ('about a topic'), and differentiates from sibling tools by mentioning the tone and brand-safety tags and the later use of `report`.

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?

The description explicitly states when to use ('any question about current events or a topic's coverage') and provides a workflow instruction (call `report` with `request_id`). It lacks explicit exclusions but gives clear context.

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