Skip to main content
Glama

Rebbel

by io.rebbel
OverviewDiscussionsAdmin

Ask for changes

ask_for_changes

Asks the department to change one thing about a post from a plain-language note — the chat equivalent of the post page's "Ask for changes". The note is classified into a scope (the caption; one slide or image; all the media; add or remove a slide, e.g. a "Download the app" closing slide; timing) and ONLY that scope is redone, through the same generation path the post was first made with. Lands as a new version of the same post with the previous version retained and restorable — never a silent no-op. A request Rebbel can't fulfil here (a channel that isn't connected, a slide that doesn't exist, a format this brand can't make) comes back as one honest line plus the choices offered, with nothing changed — the first two are decided instantly, before any generation; relay it as-is. For a post whose whole idea is wrong (not just a line or an image), use remake_post instead. Never approves or publishes: the post stays in review, and an approved/scheduled post comes back needing a fresh approve_post. Quick changes (a caption) answer inline with the caption before and after; media work keeps running — call get_post to see it land. The response's note is owner-facing and assistantHint is for you. Pass the user's own words as the note; don't rewrite the copy yourself.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteYesThe user's change request in their own words, e.g. "make the caption shorter", "different photo on slide 2", "add a Download-the-App closing slide", "post it Friday morning instead". Rebbel classifies what to change from this — pass it as said, don't pre-digest it.
postIdYesThe post's id, from list_posts.
reviewNoOnly after review_post: the reviewId it returned plus what the owner said (agreed, and when they disagreed, what was wrong / their answer to the one fact question). Omit it otherwise.
brandIdYesThe brand's id, from list_brands.
verboseNoDefault false: the compact owner view. Pass true only when you need the full stored record (every internal field, ids, provenance) — it's several times larger.
campaignIdYesAn existing campaign's id, from list_campaigns or generate_campaign.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare the mutation/safety profile; the description adds substantial behavioral detail beyond them — previous version retained and restorable, never a silent no-op, unfulfillable requests return an honest line with nothing changed (some decided instantly pre-generation), and the response's `note` (owner-facing) vs `assistantHint` (for the agent) distinction.

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?

Front-loaded with the core purpose and each clause carries real information (versioning, error behavior, note/assistantHint). It is dense and long, with several sentences that could be tightened, but little is pure filler.

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 supplies the return behavior (inline caption before/after for quick changes, get_post for media work, note vs assistantHint) and the review-gating context for a 6-param tool with a nested object. An agent has what it needs to call and interpret it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so every parameter including the nested `review` object is already documented. The description's note guidance ('pass the user's own words, don't rewrite the copy') largely duplicates the schema's own note description, so it adds little beyond the baseline.

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?

States a specific verb+resource+scope: it changes exactly one thing about a post via a plain-language note, and enumerates the classification scopes (caption, one slide/image, all media, add/remove slide, timing). It explicitly distinguishes itself from remake_post for when the whole idea is wrong.

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?

Names the alternative (remake_post) and the exact condition that selects it, notes it never approves/publishes and that an approved/scheduled post needs a fresh approve_post, and routes the agent to get_post to see media work land. Clear when-to-use and when-not.

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

All Rebbel toolsInspect
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