Mondovo

Set a reel's cover

set_post_cover

DestructiveIdempotent

The frame a reel opens on: either a cover picture (the https url of a visual that has already been made) or a moment in the clip in milliseconds — one, not both; the other is cleared. Without one the platform opens on the first frame. Free. Attaching a new clip keeps a cover picture but clears a cover moment (it named a moment in the old clip), so set a moment after attaching. For a reel's cover picture the result carries grid_check: the Instagram profile grid shows only the middle 3:4 of a 9:16 cover (y 240–1680 of 1080×1920), and status: "cut" with a warning means the cover's own words (headline, labels: text large enough to read in the grid) fall outside it — the cover is saved, but show the owner the warning. Fine print inside a pictured screen is not counted (small_text_ignored).

Input Schema

Name	Required	Description
`post_id`	Yes	The post id from get_calendar
`brand_id`	Yes	Brand workspace id from list_brands
`user_goal`	No	Optional: the user's goal behind this call, in one short sentence of plain words (e.g. "add a page so customers can book tables"). No names, emails or other personal details.
`cover_image_url`	No
`cover_thumb_offset_ms`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 30, 2026

addedInput schema / properties / user_goal

Added value: +{
+  "description": "Optional: the user's goal behind this call, in one short sentence of plain words (e.g. \"add a page so customers can book tables\"). No names, emails or other personal details.",
+  "type": "string"
+}

First observedOct 19, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations declare destructiveHint=true and idempotentHint=true, but the description adds the actual mechanics behind that destructiveness — setting one cover form clears the other, and attaching a clip silently clears a cover moment. It also discloses cost ('Free'), fallback behavior, and the return-side warning contract (`grid_check`, `status: "cut"`, `small_text_ignored`), which the agent must surface to the owner.

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 core choice is front-loaded in the first sentence and no sentence is off-topic, but the block is dense and long-breath, packing mutual exclusion, fallback, clip interaction, cost and grid geometry into one paragraph. The pixel ranges (y 240–1680 of 1080×1920) are borderline but do ground the warning semantics.

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?

There is no output schema, so the description carries the return-value burden and does so: it explains grid_check, what 'cut' plus warning means, and that the cover is still saved. For a destructive, idempotent mutation with partial schema coverage, this is complete enough for an agent to call it correctly and interpret the result.

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 60%, leaving cover_image_url and cover_thumb_offset_ms undocumented in the schema; the description compensates by explaining both (a URL of a visual already produced, versus a millisecond offset into the clip) and adds the non-obvious constraint that the image must already exist. It doesn't mention the 0–3,600,000 ms bound, which stays with the schema.

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 precise verb and resource — the frame a reel opens on — and enumerates the two mutually exclusive ways to set it (a pre-made picture URL or an in-clip moment in milliseconds). This is clearly distinguishable from sibling tools like attach_visual_to_post or attach_video_to_post, which the description implicitly separates by noting that attaching a clip clears a cover moment.

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 gives concrete usage rules: supply one of the two cover forms, not both (the other is cleared), no cover means the platform falls back to the first frame, and set a moment *after* attaching a new clip. What's missing is explicit alternative-tool routing, e.g. naming which sibling to use when no cover is wanted at all.

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

All Mondovo 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?