Skip to main content
Glama
UserClimb

UserClimb

by thomaslrw

Get a marketing playbook

get_playbook
Read-only

Fetch research-backed, app-specific marketing playbook sections to plan short-form video content, hooks, reels, and CTAs.

Instructions

The marketing playbook for one kind of app, written from research into real accounts that grew apps like it with short-form video. Sections: overview (who watches, their words, what stops them, content pillars, what to keep out), audience, reels (pillars, ways to make them, hooks, worked examples), hooks, cta, carousels (slide-by-slide shapes), platforms (and real accounts to study), examples (strong vs weak), or all.

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": {
      "app_type": "<app_type>"
    },
    "name": "get_playbook"
  }
}

Input Schema

NameRequiredDescriptionDefault
sectionNoWhich part to return. 'all' is long.overview
app_typeYesThe playbook id, from find_app_type.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine context about provenance (research into real accounts) and content orientation (strong vs weak examples), but says nothing about length/cost of 'all' or the response shape beyond the section names.

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 statement of what the tool is, followed by a compact content inventory in one sentence. It is dense but every clause carries information; the only mild redundancy is restating the enum values.

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 section inventory effectively serves as a response outline, which is the right compensation. For a simple two-parameter read tool the definition is nearly self-sufficient, missing only a note on output size and format.

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% with both parameters enum-bound and described, so the baseline is 3. The description does add meaning for the 'section' values by sketching what each contains, but it never explains 'app_type' beyond what the schema already says ('from find_app_type').

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?

States a specific resource ('the marketing playbook for one kind of app') and its basis ('written from research into real accounts that grew apps like it with short-form video'), so the agent knows what it will get. It does not distinguish itself from the sibling get_hooks even though its own 'hooks' section overlaps that tool, leaving the boundary implicit.

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?

The section list with parenthetical content notes ('platforms (and real accounts to study)', 'examples (strong vs weak)') implicitly tells an agent whether the playbook holds what it needs. However, there is no explicit when-to-use or when-not statement, and no routing to siblings such as get_hooks, get_growth_moves or get_video_structures.

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