Skip to main content
Glama

get_news

Read-onlyIdempotent

Veille quotidienne de l'utilisateur : le fil d'actualité de ses sociétés surveillées, tel qu'il apparaît sur la page Actualités de l'app Insourcia.

Utiliser cet outil pour répondre à "quoi de neuf sur ma veille ?", "qu'est-ce qui a bougé sur mes sociétés ?", "résume-moi ma veille de la semaine", ou avant de rédiger un point hebdomadaire.

Contenu : les alertes réellement délivrées (email/push) ET l'activité des sociétés des listes de veille (changements de dirigeants, annonces BODACC : procédures collectives, cessions, radiations..., articles de presse), fusionnées et dédupliquées, les plus récentes d'abord. Couvre toutes les listes de l'utilisateur, tous espaces confondus (source.espace indique lequel).

Chaque ligne est HYBRIDE : "label" donne la phrase française prête à lire (identique à l'app) et "type"/"before"/"after"/"siren"/"date" donnent les champs structurés pour filtrer ou raisonner. "date" est le jour de DÉTECTION (axe de fraîcheur) ; "effective_date", quand présent, est la date d'effet juridique.

unread_only=true ne renvoie que ce que l'utilisateur n'a pas encore lu.

"read_key" identifie chaque ligne : la passer à mark_news_read pour la marquer lue.

truncated=true signale plus de signaux que la limite demandée ; since_days et event_types permettent de resserrer (pas de pagination sur ce fil).

Si counts_are_partial=true, "total" et "unread_count" sont des PLANCHERS et non des totaux : le fil est composé sur une fenêtre bornée (les 100 dernières notifications et les 100 derniers événements), et cette fenêtre était pleine.

hidden_by_plan, quand présent, compte les signaux non retournés parce que le plan actuel ne donne accès qu'aux 10 signaux les plus récents, exactement comme la page Actualités. Un fil ainsi tronqué n'est pas complet, et hidden_by_plan dit de combien.

Réponse : { news: [...], total, unread_count, last_seen_at, since_days, truncated, url (page Actualités) }. news vide = aucun signal sur la période, ce n'est pas une erreur.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_news"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoNombre max de signaux retournés (défaut 50, max 100)
since_daysNoProfondeur d'historique en jours (défaut 90, max 365)
event_typesNoFiltre sur les types d'événements bruts. Ex: ["dirigeant_changed", "procedure_collective", "cession", "radiation", "presse"].
unread_onlyNotrue = uniquement les signaux non lus par l'utilisateur. Défaut : false.

Output Schema

NameRequiredDescriptionDefault
urlYes
newsYes
totalYes
truncatedYes
since_daysYes
last_seen_atYes
unread_countYes
hidden_by_planNo
counts_are_partialNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / event_types / description
      Previous value: -"Filtre sur les types d'evenements bruts. Ex: [\"dirigeant_changed\", \"procedure_collective\", \"cession\", \"radiation\", \"presse\"]."New value: +"Filtre sur les types d'événements bruts. Ex: [\"dirigeant_changed\", \"procedure_collective\", \"cession\", \"radiation\", \"presse\"]."
    • changedInput schema / properties / limit / description
      Previous value: -"Nombre max de signaux retournes (defaut 50, max 100)"New value: +"Nombre max de signaux retournés (défaut 50, max 100)"
    • changedInput schema / properties / since_days / description
      Previous value: -"Profondeur d'historique en jours (defaut 90, max 365)"New value: +"Profondeur d'historique en jours (défaut 90, max 365)"
    • changedInput schema / properties / unread_only / description
      Previous value: -"true = uniquement les signaux non lus par l'utilisateur. Defaut : false."New value: +"true = uniquement les signaux non lus par l'utilisateur. Défaut : false."
    • changedOutput schema / properties / news / items / properties / article / description
      Previous value: -"Lignes de type presse uniquement : l'article (titre, media, lien, resume, categorie du sujet, date de l'article, autres medias l'ayant repris)."New value: +"Lignes de type presse uniquement : l'article (titre, media, lien, résumé, catégorie du sujet, date de l'article, autres médias l'ayant repris)."
  2. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / llm_model
      Removed value: -{
      -  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
      -  "type": "string"
      -}
    • removedInput schema / required
      Removed value: -[
      -  "llm_model"
      -]
  3. Changed2 schema fields changed
    • changedInput schema / properties / event_types / description
      Previous value: -"Filtre sur les types d'evenements bruts. Ex: [\"dirigeant_changed\", \"procedure_collective\", \"cession\", \"radiation\"]."New value: +"Filtre sur les types d'evenements bruts. Ex: [\"dirigeant_changed\", \"procedure_collective\", \"cession\", \"radiation\", \"presse\"]."
    • addedOutput schema / properties / news / items / properties / article
      Added value: +{
      +  "additionalProperties": {},
      +  "description": "Lignes de type presse uniquement : l'article (titre, media, lien, resume, categorie du sujet, date de l'article, autres medias l'ayant repris).",
      +  "properties": {
      +    "date": {
      +      "type": "string"
      +    },
      +    "media": {
      +      "type": "string"
      +    },
      +    "repris_par": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "resume": {
      +      "type": "string"
      +    },
      +    "titre": {
      +      "type": "string"
      +    },
      +    "type": {
      +      "type": "string"
      +    },
      +    "url": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "titre"
      +  ],
      +  "type": "object"
      +}
  4. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / llm_model
      Added value: +{
      +  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
      +  "type": "string"
      +}
    • addedInput schema / required
      Added value: +[
      +  "llm_model"
      +]
  5. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / context
      Removed value: -{
      -  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
      -  "type": "string"
      -}
    • removedInput schema / required
      Removed value: -[
      -  "context"
      -]
  6. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / context
      Added value: +{
      +  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
      +  "type": "string"
      +}
    • addedInput schema / required
      Added value: +[
      +  "context"
      +]
  7. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description goes well beyond them: content composition and dedup rules, newest-first ordering, date meaning (detection vs effective_date), no pagination, truncated flag semantics, counts_are_partial as floors due to bounded windows, hidden_by_plan plan gating, and that an empty feed is not an error. This is exactly the kind of behavior an agent needs before calling.

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?

Purpose and trigger phrases are front-loaded, and the later paragraphs each carry distinct operational information. It runs long and the final response-shape line partly repeats what the existing output schema already provides, which is the main source of avoidable length.

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 tool with four parameters, an output schema, and non-trivial result semantics, the description covers the remaining gaps: field meanings of each hybrid row, read_key linkage to mark_news_read, truncation and plan-limited partiality, and the empty-result case. An agent has everything needed to call it and interpret its output correctly.

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?

Schema coverage is 100%, so the baseline is 3; the description earns more by explaining purpose beyond the schema text, notably that unread_only restricts to unread signals and that since_days plus event_types are the levers for narrowing when truncated, since there is no pagination. It says nothing extra about limit, so it is not fully comprehensive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource and scope: the user's daily watch feed, merged alerts and watched-company activity across all lists and workspaces. It distinguishes this from per-company tools by saying it spans 'toutes les listes de l'utilisateur, tous espaces confondus' and points to source.espace. It does not name a concrete sibling such as get_events or search_events as the alternative for raw event querying, so differentiation is contextual rather than explicit.

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?

Explicit trigger scenarios are given ('quoi de neuf sur ma veille ?', 'qu'est-ce qui a bougé sur mes sociétés ?', weekly summary prep), which is strong when-to-use guidance. There is no statement of when NOT to use it or which sibling to pick instead, leaving the boundary with get_events/search_events to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources