Skip to main content
Glama

Postemi: Social Media Scheduler

retry_post

Publish one or more failed posts again, including posts missed while a channel was disconnected (list_posts with state ERROR shows them and why they failed). Postemi decides per post whether a retry can work, and never risks posting twice: it retries at once only when nothing can have reached the platform (the media never arrived, a disconnected channel once reconnected, a platform limit once it has passed). A failure that may have happened after the platform took the post (a timeout, a server error, an unknown error) and an account problem need userConfirmed, after the user checked the platform. Content the platform refused is NOT retried: fix it with update_post. Each refusal carries the platform's exact answer (platformMessage, platformResponse). Several posts are spread two minutes apart, oldest first. Tell the user the result for each post.

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": {
      "postIds": "<postIds>"
    },
    "name": "retry_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoWhen to retry, ISO 8601 UTC. Leave out to retry now.
postIdsYespostIds of failed posts, from list_posts (state ERROR).
userConfirmedNoOnly when a previous answer asked for it and the user confirmed: that the post is not already on the platform, or that they fixed the account problem.

Output Schema

NameRequiredDescriptionDefault
errorsNo
outputNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), the description discloses the real behavioral risk model: Postemi decides per post whether a retry is safe, never risks double-posting, and gates ambiguous failures behind userConfirmed. It also notes batch pacing (two minutes apart, oldest first) and that refusals carry platformMessage/platformResponse. It does not explain rate limits or quota costs, but the safety semantics are unusually thorough.

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 action and scope are front-loaded, and the paragraph is dense with decision-relevant content rather than filler. It is long and the parenthetical examples make it slightly hard to scan, but each sentence carries operational meaning.

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 non-idempotent write tool with an output schema, the description covers the safety contract, failure taxonomy, batch behavior, and the instruction to report per-post results, with refusal details delegated to the response fields. The only gap is that it never says what happens to posts not classified as retryable in a mixed batch beyond 'Postemi decides per post'.

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, but the description adds decision logic the schema cannot: which failure classes make userConfirmed mandatory versus which retries proceed automatically, and that postIds must come from list_posts in state ERROR. The date parameter's 'retry now' default is left to the schema, which already covers 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?

The description opens with a specific verb and resource: republish one or more failed posts, including posts missed while a channel was disconnected. It also scopes the input ('list_posts with state ERROR shows them') and implicitly distinguishes itself from update_post by naming that tool as the path for content the platform refused.

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?

Explicit routing is given in both directions: use this tool for platform-limit/disconnected/media failures, and use update_post when the platform refused the content. It also states precisely when the userConfirmed flag is required (timeout, server error, unknown error, account problems) and that the user must have checked the platform first.

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.