viraldar

Overview Schema Source Related Servers Discussions Admin

Détail d'un post

post

Fetch TikTok video stats—likes, shares, saves, sound, discovery keywords, sample comments, and saved notes—by ID or URL to see why it performed.

Instructions

Toutes les stats d'un post de la base (likes, partages, enregistrements, son, mots-clés qui l'ont trouvé, exemples de commentaires qui demandent l'app, ta note s'il est gardé). Prend un id ou une URL TikTok. Un post déjà rendu par un autre outil pendant cette session ne coûte rien ; sinon il faut son URL (avec le @compte) : il est cherché parmi les posts de ce compte, dans le quota.

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": {
      "post": "<post>"
    },
    "name": "post"
  }
}

Input Schema

Name	Required	Description	Default
`post`	Yes	Id du post, ou son URL TikTok.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 11, 2026

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 burden and does well: it discloses a cost/quota model, that repeats within a session are free, that a non-cached post must be looked up among that account's posts, and that this consumes quota. It does not cover failure behavior (e.g. what happens if the URL lacks @account or the post is not found), which keeps it from a 5.

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?

Front-loaded with what is returned, then the accepted input, then the cost/lookup rule — a logical order with no filler. It is dense (parenthetical enumeration plus two conditional clauses) but every sentence carries information the agent needs.

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?

No output schema exists, so the description must describe return values, and it does so field by field, plus it covers the quota and caching behavior that affects whether the call is worth making. Remaining gaps are edge-case behavior (invalid URL, post not found), which are secondary for a single-parameter read tool.

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% and the single parameter is documented as 'Id du post, ou son URL TikTok'. The description adds real meaning beyond the schema by specifying the URL must include the @account and explaining that the id/URL choice affects lookup cost, which the schema alone does not convey.

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 resource (a post from the database) and enumerates exactly what is returned: likes, shares, saves, sound, keywords, sample comments asking for the app, and the user's own rating. An agent can distinguish this from sibling tools like 'noter_post' or 'chercher_posts' because the description is framed as full detail retrieval for one post rather than searching or annotating.

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?

Gives clear selection context: use it to get all stats for one post, and prefer posts already returned earlier in the session since those cost nothing. It also explains the fallback path (provide the TikTok URL with @account) when the post has not been seen. It stops short of naming a concrete alternative tool or saying when not to use it, so it is not a full 5.

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