Skip to main content
Glama

ingest_event

Idempotent

Feed finance news into a graded event ledger mapped to affected symbols for committee RAG recall; provide a one-line claim, stance, and severity to store without backend model normalization.

Instructions

Feed a finance news item you (the host agent) found into the event ledger, graded and mapped to affected symbols, stored for committee RAG recall.

Preferred: normalize it yourself — pass one_line_claim, stance, severity (and ideally affected_symbols). The backend then only validates and stores it; no backend model is involved. Without those fields the backend model normalizes it, which fails when the backend runs keyless (agent mode) — you get an error telling you which fields to add.

You have far better search reach than the self-hosted crawler (including Chinese-language sources) — proactively feed news relevant to the user's holdings, especially A-share/regional coverage the crawler misses. Identical source snapshots are idempotent. Material corrections retain versions; a shared topic or URL never proves a correction is duplicate. Structured input needs no backend LLM key and grants no learning permission.

Args: title: Headline of the news item. url: Canonical source URL (also the dedup key). snippet: Short excerpt or summary of the article body. source: Publisher name (e.g. "Reuters") — the news outlet. published_at: ISO 8601 publication time, if known. ingested_by: Your own agent identity (e.g. "hermes") for provenance; distinct in meaning from source.

Returns: Ingestion result with the normalized event id(s), dedup status, and committee_task_id — set when a new holding-relevant event (severity ≥ mid, non-neutral) triggered a rate-limited committee re-run. In agent mode it is "queued:": the re-run waits for you in pending_committees. This tool is disabled in advisory mode.

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": {
      "title": "<title>",
      "url": "<url>"
    },
    "name": "ingest_event"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesPublisher URL or backend-issued source locator from pending_news. A snapshot locator requires binding to this instance's captured original.
titleYesHeadline of the news item.
sourceNoPublisher name (e.g. 'Reuters') — the news outlet.
stanceNoFor the holdings: 'risk', 'opportunity' or 'neutral'. Required with one_line_claim.
snippetNoOriginal source excerpt copied verbatim; keep your interpretation in one_line_claim and assessed labels.
entitiesNoKey entities (countries, companies, central banks), lowercase.
severityNo'low', 'mid' or 'high'. Required with one_line_claim.
event_typeNoe.g. 'macro', 'policy', 'earnings', 'geopolitics', 'commodity', 'other'.
ingested_byNoYour own agent identity (e.g. 'hermes') for provenance; distinct from source.host-agent
published_atNoISO 8601 publication time, if known.
one_line_claimNoYour one-sentence factual summary. Fill this (plus stance and severity) to ingest without any backend model — preferred.
affected_symbolsNoyfinance tickers the event materially affects, e.g. ['GC=F'].
source_snapshot_idNoExact pending_news source snapshot to bind. Original source fields remain immutable; labels are your interpretation.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.68.10
    • changedInput schema / properties / snippet / description
      Previous value: -"Short excerpt or summary of the article body."New value: +"Original source excerpt copied verbatim; keep your interpretation in one_line_claim and assessed labels."
    • addedInput schema / properties / source_snapshot_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Exact pending_news source snapshot to bind. Original source fields remain immutable; labels are your interpretation.",
      +  "title": "Source Snapshot Id"
      +}
    • changedInput schema / properties / url / description
      Previous value: -"Canonical source URL (also the dedup key)."New value: +"Publisher URL or backend-issued source locator from pending_news. A snapshot locator requires binding to this instance's captured original."
  2. Changed6 schema fields changedv0.45.1
    • addedInput schema / properties / affected_symbols
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "yfinance tickers the event materially affects, e.g. ['GC=F'].",
      +  "title": "Affected Symbols"
      +}
    • addedInput schema / properties / entities
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Key entities (countries, companies, central banks), lowercase.",
      +  "title": "Entities"
      +}
    • addedInput schema / properties / event_type
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "e.g. 'macro', 'policy', 'earnings', 'geopolitics', 'commodity', 'other'.",
      +  "title": "Event Type"
      +}
    • addedInput schema / properties / one_line_claim
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Your one-sentence factual summary. Fill this (plus stance and severity) to ingest without any backend model — preferred.",
      +  "title": "One Line Claim"
      +}
    • addedInput schema / properties / severity
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "'low', 'mid' or 'high'. Required with one_line_claim.",
      +  "title": "Severity"
      +}
    • addedInput schema / properties / stance
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "For the holdings: 'risk', 'opportunity' or 'neutral'. Required with one_line_claim.",
      +  "title": "Stance"
      +}
  3. Addedv0.34.0
  4. Removedv0.31.7
  5. Changed6 schema fields changedv0.31.4
    • addedInput schema / properties / ingested_by / description
      Added value: +"Your own agent identity (e.g. 'hermes') for provenance; distinct from source."
    • addedInput schema / properties / published_at / description
      Added value: +"ISO 8601 publication time, if known."
    • addedInput schema / properties / snippet / description
      Added value: +"Short excerpt or summary of the article body."
    • addedInput schema / properties / source / description
      Added value: +"Publisher name (e.g. 'Reuters') — the news outlet."
    • addedInput schema / properties / title / description
      Added value: +"Headline of the news item."
    • addedInput schema / properties / url / description
      Added value: +"Canonical source URL (also the dedup key)."
  6. First observedv0.31.0

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations (idempotentHint=true, destructiveHint=false) by explaining the dedup model: identical snapshots are idempotent, material corrections retain versions, and a shared topic or URL never proves duplication. It also discloses the side effect that a severity ≥ mid, non-neutral holding-relevant event triggers a rate-limited committee re-run with a 'queued:<id>' task, and that structured input grants no learning permission.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening paragraph is well front-loaded and the mode/dedup warnings earn their space, but the Args and Returns blocks duplicate the input schema and the existing output schema almost line for line. Roughly a third of the text is restatement rather than added signal.

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?

For a 13-parameter mutation with a committee side effect, the description covers the failure mode an agent will actually hit (keyless backend), the mode restriction, dedup/versioning semantics, and the meaning of the returned committee_task_id. Nothing an agent needs in order to call it correctly is missing.

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 description coverage is 100%, so the schema already documents every parameter, and the Args block largely restates it. The description does add two genuinely new facts — that url is also the dedup key, and that ingested_by is semantically distinct from source — which is enough to hold the 3 baseline but not to exceed it.

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?

States a specific verb and resource ('feed a finance news item into the event ledger') plus the transformation applied (graded, mapped to affected symbols, stored for RAG recall). It is clearly separable from the crawler-driven siblings (collect_news, pending_news, add_news_source) which gather rather than ingest agent-found items.

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?

Explicitly says when to use the structured path ('Preferred: normalize it yourself — pass one_line_claim, stance, severity') and what happens otherwise (backend model runs, fails when keyless), plus a proactive-use directive about holdings relevance and A-share/regional coverage the crawler misses. It also states an exclusion: disabled in advisory mode.

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