Skip to main content
Glama
UserClimb

UserClimb

by thomaslrw

Check a draft for AI tells

check_draft
Read-only

Scores hooks, scripts, captions, or carousels out of 100 for human readability, then lists specific fixes like AI-sounding words, generic openers, em dashes, and missing asks before publishing.

Instructions

Scores a hook, script, caption or carousel out of 100 for how human it reads and lists what to fix: AI-sounding words, em dashes, generic openers, the app's name in the hook, nothing specific, even sentence rhythm, no ask, and more. Instant and local. Run it on everything before showing it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "check_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoany
textYesThe draft to check.
app_nameNoOptional. Flags the app's name in the hook.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true and openWorldHint=false; the description adds real context on top: a 0-100 scoring scale, an enumerated defect checklist (AI words, em dashes, generic openers, app name in hook, vague specifics, flat rhythm, missing ask), and that the check runs instantly and locally. It does not say whether the flagged text is quoted or returned with locations, which keeps it below 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?

Front-loaded with the core action and result, then a compact defect list, then two short operational sentences. The checklist is slightly long and trailed by a vague 'and more', but every clause carries information an agent would otherwise have to guess.

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 does the job of explaining the return (a score out of 100 plus fixes), and it states the non-networked, instant behavior. Only minor gaps remain — directionality of the score is implied rather than stated, and it does not say that app_name must be supplied for the app-name check to fire.

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 67%, below the high-coverage baseline, so the description must carry weight — and it does: the four named draft types implicitly document the 'kind' enum, which the schema leaves undescribed, and 'the app's name in the hook' reinforces what app_name triggers. The 'text' parameter is left entirely to the schema, but its meaning is self-evident.

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?

Uses a specific verb and resource ('Scores a hook, script, caption or carousel out of 100') and names the concrete output (a score plus a list of what to fix). That is unmistakably distinct from the generation-flavored siblings like get_hooks or writing_method, so an agent can place it without opening the 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?

'Run it on everything before showing it' gives a clear trigger point (pre-publish review) and implies it applies to all generated copy. It stops short of naming an alternative or stating when not to run it, so it is strong context without full routing guidance.

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