Skip to main content
Glama
Sign In
viraldar

viraldar

by ThomasRayvol
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Chercher dans la base viraldar

chercher_posts

Search curated viral TikTok posts (100K+ views) by words, themes, language, views, outlier, date, account size, format, or app-demand signals, then sort results to identify replicable content ideas.

Instructions

Cherche parmi les posts TikTok viraux (≥ 100 k vues) déjà relevés par viraldar — jamais sur TikTok lui-même : si rien ne sort, la base n'a pas encore ce sujet (la recherche vide est notée pour le prochain relevé). Filtres : mots, thèmes, langue, vues, outlier, date, taille du compte, format, 📲. Tri au choix. 24 posts par page, chacun avec son URL TikTok, ses vues, son outlier (avec la médiane du compte et son n), vues ÷ abonnés, 📲, thèmes, langue, date. Compte dans le quota du jour (600 posts distincts). Pour des idées à reproduire sur de petits comptes, préfère petits_comptes_viraux.

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": "chercher_posts"
  }
}

Input Schema

NameRequiredDescriptionDefault
triNoscore = les plus prometteurs (défaut) ; outlier = le plus au-dessus de sa médiane ; ratio_abonnes = vues ÷ abonnés ; publie = les plus récents.
motsNoTous ces mots, dans le texte, le compte ou les mots-clés (accents ignorés).
pageNo0 = première (24 posts) ; chaque post neuf compte dans le quota.
detailNoToutes les stats, texte entier.
formatNo
themesNoClés de thèmes (infos_base), l'un OU l'autre.
languesNo
likes_okNoLikes ≥ 2 % des vues (sinon souvent de la pub).
vues_minNo
mes_themesNoAjoute les thèmes de l'utilisateur.
abonnes_maxNo
demande_appNo📲 : des commentaires demandent le nom de l'app.
outlier_minNovues ÷ médiane du compte, minimum (ex. 5).
publie_depuis_joursNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses quota accounting (600 distinct posts per day, each new post counted), page size of 24, and the side effect that empty searches are recorded for future collection. Gaps remain — nothing about authentication requirements or rate limits, and no indication of what happens on very deep pages.

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 dense but front-loaded with the core scoping and empty-result caveat before filters, page size, and the sibling pointer. The long enumeration of returned fields is slightly list-like, but given there is no output schema it earns its space.

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?

For a 14-parameter tool with no output schema and no annotations, this covers the essentials: data source, empty-result meaning, return fields (substituting for an output schema), pagination, quota cost, and an alternative tool. The remaining gap is parameter-level semantics for the undocumented filters, which the description only gestures at by category.

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 64%, so roughly five params (`format`, `langues`, `vues_min`, `abonnes_max`, `publie_depuis_jours`) have no schema-level explanation. The description compensates partially by enumerating the filter families (langue, vues, taille du compte, date, format), but it does so at name level only, adding no syntax, units, or boundary semantics beyond that.

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 precise verb and resource — searching previously collected viral TikTok posts (≥100k views) in the viraldar database — and explicitly negates the wrong reading ('jamais sur TikTok lui-même'). It also distinguishes itself from the sibling `petits_comptes_viraux` by naming the case where that sibling is preferred.

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?

It gives explicit when-to-use context and an important when-result-is-empty rule: an empty search means the topic isn't in the base yet and the query is logged for the next collection. It also routes the agent to `petits_comptes_viraux` for small-account reproduction ideas, which is exactly the kind of sibling disambiguation that prevents misfires.

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

Deploy Server

Other Tools