Skip to main content
Glama
Hermoso

Hermoso

Official

Save a playbook

save_playbook

Save reusable strategy takeaways—hooks, angles, formats, and concrete plays—as a playbook in the Playbooks library. Bank proven creative from a competitor teardown or angle mining so you can re-run what works.

Instructions

Save a reusable PLAYBOOK — the strategy takeaways worth re-running: the hooks that work, the angles, the formats, and the concrete plays. Use it to keep what a competitor_teardown or mine_angles just found, or to bank a creative you want to repeat. Lands in the same Playbooks library the web app lists, runs and manages. Distinct from save_skill (a directive applied to every ad) and from the swipefile (raw saved creative). Free.

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": {
      "name": "<name>"
    },
    "name": "save_playbook"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesthe playbook headline — what it is, in a few words
brandNoprofile id/name from list_brands, this call only
hooksNothe opening hooks worth reusing, verbatim
playsNothe concrete plays to run ({title, detail}) — the actionable half
anglesNothe persuasion angles ({title, detail})
sourceNowhere it came from, e.g. “teardown · Ridge”
formatsNothe formats/recipes this plays best in (e.g. ugc_selfie, cinematic, static)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.465
    • addedInput schema / properties / angles / items / properties / detail / description
      Added value: +"what the angle is and why it persuades; optional, up to 600 characters"
    • addedInput schema / properties / angles / items / properties / title / description
      Added value: +"the angle, in a few words"
    • addedInput schema / properties / plays / items / properties / detail / description
      Added value: +"how to run the play; optional, up to 600 characters"
    • addedInput schema / properties / plays / items / properties / title / description
      Added value: +"the play to run, in a few words"
  2. Changed1 schema field changedv0.1.374
    • changedInput schema / properties / brand / description
      Previous value: -"brand id/name from list_brands, this call only"New value: +"profile id/name from list_brands, this call only"
  3. Changed1 schema field changedv0.1.371
    • changedInput schema / properties / brand / description
      Previous value: -"which brand this is for (defaults to the workspace brand)"New value: +"brand id/name from list_brands, this call only"
  4. Addedv0.1.161

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare the safety profile (not read-only, non-destructive, closed-world), so the description's job is to add destination and cost context — and it does: it lands in the same Playbooks library the web app lists and runs, and it is free. It does not address what happens on a duplicate name (idempotentHint is false), which is the one behavior an agent might reasonably need.

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?

Three sentences, front-loaded with the definition before the usage and differentiation clauses. Dense but every sentence carries a distinct payload; only minor trimming (e.g. the appending 'Free.') would tighten it further.

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?

For a seven-parameter, fully-described write tool with no output schema, the description covers purpose, content shape, destination library, alternatives, and cost. The remaining gap — dedupe/overwrite behavior and what the call returns — is minor and partly implied by the non-idempotent annotation.

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 seven parameters are already documented. The description's enumeration of hooks, angles, formats and concrete plays loosely maps to those fields but adds no syntax, ordering, or required-vs-optional nuance beyond the schema. Baseline 3 applies.

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 (save) and resource (playbook), then immediately defines what a playbook contains — hooks, angles, formats, concrete plays. It also explicitly names what it is not (save_skill, swipefile), so the agent can distinguish it from the nearest siblings without opening schemas.

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

Usage Guidelines5/5

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

Gives concrete trigger contexts: 'keep what a competitor_teardown or mine_angles just found' or 'bank a creative you want to repeat.' It also names two alternatives and the axis of difference (directive applied to every ad vs raw saved creative), leaving nothing to inference.

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

Deploy Server

Other Tools