Skip to main content
Glama

Mark

by com.use-mark.app
OverviewDiscussionsAdmin

Check Draft

check_draft
Read-onlyIdempotent

Runs Mark's content checks on draft text without saving it (six on every channel, plus two on a competitor_page): exclusion (phrases this workspace blocks or warns on), char_limit, required_meta, ai_fluff (generic AI-sounding words), unsourced_number (percentages, money and multipliers no active claim states), and placeholder (a marker left for the writer, such as [needs source], [TBD] or a bare TODO, ignored inside code, link targets and URLs; it fails). A competitor_page also gets table (a markdown table; it fails, use headings and lists) and open_placeholder (a [confirm: …] fact left to confirm; it fails), and its unsourced_number fails instead of warning. Each result is pass, warn or fail with the matched text, field and position; exclusion matches carry the rule's reason. A fail is what submit_post refuses on a draft; warnings never block. For an X thread, pass assetIds to check each post's media too. Uses this workspace's active exclusions and claims. Writes nothing. Related: save_post, get_channel_rules, get_brand_context, list_claims.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyYesDraft body / caption.
metaNoChannel-specific fields from get_channel_rules.
channelYesChannel id such as linkedin or blog.
assetIdsNoX threads: the asset ids save_post would get, so required_meta checks each post's media (4 images, or 1 video, or 1 GIF) with meta.threadMedia.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
checksYesMark's content checks on the saved content: exclusion, char_limit, required_meta, ai_fluff, unsourced_number, placeholder, and on a competitor_page also table and open_placeholder. On a draft, a fail stops submit_post; warn never does.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / channel / enum
      Previous value: -[
-  "instagram",
-  "facebook",
-  "youtube",
-  "pinterest",
-  "tiktok",
-  "x",
-  "linkedin",
-  "blog",
-  "faq",
-  "competitor_page",
-  "landing_page",
-  "email",
-  "meta_ads",
-  "google_ads"
-]New value: +[
+  "instagram",
+  "facebook",
+  "youtube",
+  "pinterest",
+  "tiktok",
+  "x",
+  "linkedin",
+  "linkedin_article",
+  "blog",
+  "faq",
+  "competitor_page",
+  "landing_page",
+  "email",
+  "meta_ads",
+  "google_ads"
+]
  2. Changed2 schema fields changed
    • changedOutput schema / properties / checks / description
      Previous value: -"Mark's content checks on the saved content: exclusion, char_limit, required_meta, ai_fluff, unsourced_number, placeholder. On a draft, a fail stops submit_post; warn never does."New value: +"Mark's content checks on the saved content: exclusion, char_limit, required_meta, ai_fluff, unsourced_number, placeholder, and on a competitor_page also table and open_placeholder. On a draft, a fail stops submit_post; warn never does."
    • changedOutput schema / properties / checks / items / properties / checkId / enum
      Previous value: -[
-  "exclusion",
-  "char_limit",
-  "required_meta",
-  "ai_fluff",
-  "unsourced_number",
-  "placeholder"
-]New value: +[
+  "exclusion",
+  "char_limit",
+  "required_meta",
+  "ai_fluff",
+  "unsourced_number",
+  "placeholder",
+  "table",
+  "open_placeholder"
+]
  3. Changed1 schema field changed
    • addedInput schema / properties / assetIds
      Added value: +{
+  "description": "X threads: the asset ids save_post would get, so required_meta checks each post's media (4 images, or 1 video, or 1 GIF) with meta.threadMedia.",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 100,
+  "type": "array"
+}
  4. Changed2 schema fields changed
    • changedOutput schema / properties / checks / description
      Previous value: -"Mark's content checks on the saved content: exclusion, char_limit, required_meta, ai_fluff, unsourced_number. On a draft, a fail stops submit_post; warn never does."New value: +"Mark's content checks on the saved content: exclusion, char_limit, required_meta, ai_fluff, unsourced_number, placeholder. On a draft, a fail stops submit_post; warn never does."
    • changedOutput schema / properties / checks / items / properties / checkId / enum
      Previous value: -[
-  "exclusion",
-  "char_limit",
-  "required_meta",
-  "ai_fluff",
-  "unsourced_number"
-]New value: +[
+  "exclusion",
+  "char_limit",
+  "required_meta",
+  "ai_fluff",
+  "unsourced_number",
+  "placeholder"
+]
  5. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, and the description reinforces this with 'Writes nothing' while adding genuine context: the per-channel composition of checks, the fail-vs-warn distinction and its blocking consequence, competitor_page-specific failures, and that exclusion matches carry the rule's reason. This goes well beyond the structured safety hints.

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 purpose and non-saving behavior are front-loaded, and the trailing 'Related:' line is efficient. The dense parenthetical enumerations of checks are information-rich but heavy; a slightly tighter structure would read better, though little is wasted.

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 an output schema present, the description need not describe return shapes, and it still covers result states, matched-text/field/position, workspace exclusion and claim sourcing, and cross-channel differences. Nothing an agent needs to call it correctly is missing.

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, but the description adds real meaning: it explains the assetIds usage condition (X thread media validated as 4 images / 1 video / 1 GIF) and ties meta to required_meta and get_channel_rules. That exceeds what the schema text alone conveys.

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 and resource ('Runs Mark's content checks on draft text without saving it') and enumerates exactly what is checked per channel, which cleanly separates it from write-oriented siblings like save_post and submit_post. An agent can distinguish this from save_post without opening either schema.

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 tells the agent the outcome matters for submission ('A fail is what submit_post refuses on a draft; warnings never block'), and it names related tools (save_post, get_channel_rules, get_brand_context, list_claims), plus a condition for assetIds on X threads. It stops short of an explicit 'use this before calling submit_post instead of X' statement, so it is clear context but not a full when/when-not rulebook.

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

All Mark 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