Skip to main content
Glama
Sign In

craft-content-mcp

by io.github.shashwatgtm
OverviewDiscussionsAdmin

CRAFT Content Improver

craft_content_improver
Read-only

Helps you decide whether a draft is ready to publish and what to fix first, from the pasted copy and its content type. Optional goal, audience and tone preference refine the review. Returns a score for each area (buzzwords, claims that need proof, fragments, unfilled merge fields, claims about the reader, a missing figure or ask) with each deduction quoted from your text, and the edits it made. If it finds nothing to edit, it says so and prints no improved version.

Input Schema

NameRequiredDescriptionDefault
goalNoOptional: what the content should achieve (for example 'book a first meeting' or 'educate readers'). If not given, a goal is chosen from the content type
contentYesThe content to review
audienceNoOptional: who the content is for. The review reports when the text never mentions them
your_sectorNoOptional: your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear.
content_typeYesThe kind of content; it changes which checks apply
tone_preferenceNoThe tone you want. Only more_formal and more_casual are checked in the text; any other value is named in the answer as not used

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / audience / description
      Previous value: -"OPTIONAL: Who is this content for? Helps tailor improvements."New value: +"Optional: who the content is for. The review reports when the text never mentions them"
    • changedInput schema / properties / content / description
      Previous value: -"Content to analyze"New value: +"The content to review"
    • changedInput schema / properties / content_type / description
      Previous value: -"Type of content affects evaluation criteria"New value: +"The kind of content; it changes which checks apply"
    • changedInput schema / properties / goal / description
      Previous value: -"OPTIONAL: What should this content achieve? (e.g., 'drive signups', 'educate readers'). If not given, a goal is chosen from the content type (for example 'Get meetings booked' for a sales email)"New value: +"Optional: what the content should achieve (for example 'book a first meeting' or 'educate readers'). If not given, a goal is chosen from the content type"
    • changedInput schema / properties / tone_preference / description
      Previous value: -"Desired tone (accepted for compatibility; it does not change the analysis)"New value: +"The tone you want. Only more_formal and more_casual are checked in the text; any other value is named in the answer as not used"
    • addedInput schema / properties / your_sector
      Added value: +{
+  "description": "Optional: your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear.",
+  "enum": [
+    "logistics_tech",
+    "fintech",
+    "saas",
+    "vertical_saas",
+    "ai_native",
+    "ites",
+    "telecom",
+    "software",
+    "cybersecurity",
+    "other"
+  ],
+  "type": "string"
+}
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, destructiveHint false, openWorldHint false), so the bar is lower, and the description still adds real behavior: it enumerates the scored areas, notes that each deduction is quoted from the text, and discloses the edge case that nothing-to-edit yields no improved version. It stops short of describing the score scale or output shape, which keeps it from a 5.

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 the return behavior are front-loaded, and the closing sentence covers the meaningful empty-result case rather than padding. The parenthetical list of scored areas is long but each item is informative, so little is wasted.

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?

With no output schema, the description carries the burden of explaining returns and does so: per-area scores, quoted deductions, and the edits made, plus the no-op behavior. What remains unstated is the scoring scale and whether the improved version is returned alongside the report, which an agent might want before calling.

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 description coverage is 100%, so all six parameters including the three enums are already well documented in the schema itself. The description only restates that goal, audience and tone preference 'refine the review,' adding no syntax or interpretation guidance beyond that baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: it reviews a draft and tells you 'whether a draft is ready to publish and what to fix first,' driven by 'the pasted copy and its content type.' That is clearly distinct from the generator-oriented siblings (case_study_generator, newsletter_builder, webinar_script), though it never names a sibling to route away from.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the phrase 'decide whether a draft is ready to publish,' which suggests a pre-publish review gate, and the optional goal/audience/tone parameters are framed as refinements. There is no explicit statement of when NOT to use it, no mention of alternatives among the sibling tools, and no prerequisite context.

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

All craft-content-mcp 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