Pith - Instagram Publishing

Approve / reject / edit / schedule a draft

update_draft

The approval-inbox verb. action=approve (optionally with schedule_at 'HH:mm' in the account's timezone), reject, edit (requires overlay_lines and/or overlay_spec; implies approval), unschedule (clears a pending schedule), or convert_to_reel (Pro plan). Terminal drafts (published/rejected/failed) cannot be changed.

Input Schema

TableJSON Schema

Name	Required	Description
`action`	Yes
`handle`	No	Instagram handle (with or without @). Omit for your default account.
`reason`	No	reject only: why, in the owner's words. Stored on the draft and fed back into the next generation.
`context`	Yes	Explain why you are calling this tool and how it fits into the business owner's goal for their Instagram presence. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include personal data, credentials, or the text of a draft. Example (20 words): "Reviewing the pending drafts before approving today's story, checking the caption matches the photo the owner expects."
`draft_id`	Yes
`schedule_at`	No	'HH:mm' in the tenant's timezone — schedules publish when approving.
`overlay_spec`	No	Structured overlay spec from the composite editor (version 1).
`overlay_lines`	No	Replacement story text lines (edit action).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 29, 2026

addedInput schema / properties / reason

Added value: +{
+  "description": "reject only: why, in the owner's words. Stored on the draft and fed back into the next generation.",
+  "maxLength": 500,
+  "type": "string"
+}

First observedSep 20, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the description carries real weight and delivers: edit implicitly approves, unschedule clears a pending schedule, convert_to_reel requires a Pro plan, and terminal drafts are immutable. These are meaningful behavioral constraints beyond the annotations, though return behavior is unstated.

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?

Very economical — one dense paragraph with each parenthetical earning its place, and the action list is front-loaded. The heavy use of compressed parentheticals makes it slightly harder to scan than a clean numbered list would, but there is no wasted text.

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 an 8-parameter dispatcher tool with nested objects and no output schema, the description covers the action semantics and mutation constraints an agent needs to call it correctly. The one gap is what happens on success (e.g. whether edit re-renders the draft), but annotations and schema otherwise fill the space.

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 75%, and the description adds genuine semantics on top: schedule_at is 'HH:mm' in the account timezone, reason is reject-only, and edit requires overlay_lines and/or overlay_spec. It explains the action enum's side effects rather than just listing values, going beyond what the schema states.

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 'The approval-inbox verb' and then enumerates all five actions (approve, reject, edit, unschedule, convert_to_reel) with their individual effects. This clearly separates it from siblings like publish_draft, get_draft, and regenerate_draft, which handle different points in the draft lifecycle.

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?

It states action-specific requirements (edit needs overlay_lines and/or overlay_spec, reject takes a reason, schedule_at only applies with approve) and gives an explicit when-not: 'Terminal drafts (published/rejected/failed) cannot be changed.' It does not, however, route to sibling tools such as regenerate_draft or publish_draft.

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

All Pith - Instagram Publishing tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?