Skip to main content
Glama

Garder ou passer un post

trier_post

Triage recently shown TikTok posts as keep, skip, or clear, and add a note on what to reuse for future content.

Instructions

Comme les boutons du site : « garder » met le post dans À reproduire (avec une note facultative : ce qu'on en reprend — hook, structure, visuel, son), « passer » le sort des recommandés, « retirer » efface le tri. Seul un post déjà montré à l'utilisateur ces 2 derniers jours (rendu par un outil de recherche) peut être trié.

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>",
      "action": "<action>"
    },
    "name": "trier_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoAvec « garder » : ce que l'utilisateur en reprend.
postYesId ou URL du post.
actionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
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 discloses real behavior beyond the schema: the eligibility window, and the distinct side effect of each of the three actions including removal from recommendations and erasure of prior triage. Gaps remain on error behavior when the precondition is violated and whether « retirer » also discards the stored note.

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?

A single dense paragraph, front-loaded with the site-button analogy and then the three action semantics, followed by the eligibility rule. No filler sentences, though the analogy sentence is doing modest work and could be trimmed.

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 3-parameter mutation tool with no annotations and no output schema, the definition covers preconditions and per-action effects adequately. It omits what is returned on success and the failure mode when the post is not eligible, which is the main remaining gap.

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 67%, so the description must add value, and it does: it explains that the note is optional and should record what is being reused (hook, structure, visual, sound), and it defines the effect of each action value rather than just listing them. The post id/URL parameter is left to the schema.

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 verb (trier) and resource (post) and then maps all three enum actions to concrete outcomes: « garder » moves the post into À reproduire, « passer » removes it from recommendations, « retirer » clears the triage. It also ties « garder » to the sibling concept of À reproduire, so the agent can distinguish this from noter_post or a_reproduire. It stops short of naming the search sibling (chercher_posts) that produces eligible posts.

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?

A hard usage precondition is given: only a post already shown to the user in the last 2 days via a search tool may be triaged. That is a clear when-to-use constraint plus implied when-not. It does not explicitly name which sibling to call first or what to do if the precondition fails.

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