Write one platform-native post from an idea, grounded in the Brain (the workspace's, unless brain_id names another). Draws one AI generation.
| Name | Required | Description | Default |
|---|---|---|---|
| idea | Yes | ||
| brain_id | No | ||
| platform | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It discloses that the tool writes exactly one post, grounds content in the Brain, defaults to the workspace Brain, allows a different Brain via brain_id, and consumes one AI generation. It stops short of saying whether the post is a draft or immediately publishable, but the sibling names make that distinction inferable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two compact sentences front-load the action, then add the grounding behavior and the one-generation cost. Every sentence earns its place, and there is no redundant restating of the tool name or schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers core purpose, input source, Brain defaulting, and generation cost. But it omits platform parameter semantics and the post's lifecycle stage, which is relevant given the sibling tools schedule_post and publish_now. It is adequate but leaves meaningful gaps for an agent deciding how to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. 'idea' is effectively explained by 'from an idea', and brain_id is explicitly explained via 'unless brain_id names another'. However, the platform parameter is not directly explained beyond the word 'platform-native', leaving its accepted values and default behavior unclear.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific action ('Write') and a specific resource ('one platform-native post'), plus the source ('from an idea') and grounding context (the Brain). It does not explicitly call out sibling tools, but the action is clearly distinguishable from schedule_post, publish_now, and query_brain.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use the tool: when you have an idea and want one grounded post generated. It also explains the brain default and override. However, it gives no explicit guidance about when not to use it or when to prefer siblings like schedule_post or publish_now.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct action in the content workflow: planning, composing, approving, scheduling, canceling, publishing, querying, and analytics. Even similar actions like schedule_post and publish_now are clearly separated by timing and irreversibility.
Tool names consistently use snake_case verbs followed by nouns (list_channels, compose_post, cancel_scheduled_post). The pattern is predictable and makes resource-action relationships easy to infer.
14 tools is well-scoped for a content planning and social publishing server. Each tool covers a meaningful step in the workflow without redundant or excessive additions.
The set covers the core content lifecycle: plan, compose, approve, schedule, publish, cancel, and analyze. Minor gaps exist around editing existing drafts or directly modifying plan items, but these can be worked around with the provided tools.