Skip to main content
Glama
FirstReply MCP Server

FirstReply MCP Server

Official
by FirstReply

Post Write

post_write
Read-onlyIdempotent

Generate, shorten, or rewrite social media post text from an instruction or existing copy, with optional platform and character limits. The result is not saved; pass it to create or schedule.

Instructions

Write the text of a social media post with the organization's AI: WRITE a post from an instruction (facts come from the knowledge base), or SHORTEN or REWRITE a text. Returns the text, with tooLong when it still exceeds maxLength. Nothing is saved: pass the text to post_create or post_schedule.

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": {
      "organizationId": "<organizationId>",
      "action": "<action>"
    },
    "name": "post_write"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoThe text to shorten or rewrite (required for SHORTEN and REWRITE); for WRITE an optional starting point.
actionYesWRITE a new post from the instruction, SHORTEN or REWRITE the text.
languageNoTwo-letter language code. Default: the organization's language.
platformNoType of the channel the text is for (see channel_list), e.g. MESSENGER (Facebook Page), INSTAGRAM or LINKEDIN. Omit for a text that works on several platforms.
maxLengthNoCharacter limit to stay within, e.g. 280 for X.
instructionNoWRITE: what the post is about. SHORTEN, REWRITE: how to change the text, e.g. "more casual".
organizationIdYesThe organization id. Use organization_list to find it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.3.0

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description corroborates this with 'Nothing is saved', which is the key behavioral fact for an agent that might otherwise assume persistence. It also adds return-value behavior ('Returns the text, with tooLong when it still exceeds maxLength') and notes that facts come from the knowledge base, consistent with openWorldHint=false. It does not cover cost, latency, or failure modes of the underlying AI call, so it stops short of 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences, front-loaded with the three modes and closed with the no-persistence routing rule. Every clause carries information: modes, return shape, and next step. No filler or restatement of the title.

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?

With no output schema, the description still discloses the return value and the meaning of tooLong, and it covers the multi-mode invocation pattern of a 7-parameter tool. Combined with annotations that already cover safety and idempotency, an agent has everything needed to call it correctly and to route its output onward.

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 adds meaning on top by tying action values to which inputs matter (instruction for WRITE, text for SHORTEN/REWRITE) and by linking maxLength to the tooLong return flag. That conditional coupling between parameters is useful semantics the schema states only piecewise, though it does not explain language or platform fallbacks beyond what the schema already documents.

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 specific verb and resource ('Write the text of a social media post with the organization's AI') and immediately enumerates the three modes: WRITE from an instruction, SHORTEN, and REWRITE. It also distinguishes itself from post_create and post_schedule by declaring 'Nothing is saved', so an agent can tell it apart from real persistence tools without opening the schema.

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 guidance for each action ('WRITE a post from an instruction', 'SHORTEN or REWRITE a text') and an explicit follow-up rule: pass the output to post_create or post_schedule rather than expecting a saved post. The boundary against the persistence siblings is stated outright, leaving nothing to inference.

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