eightytwenty

Find reference slides

find_references

Read-only

Use after the slide's claim is settled, to inform the layout options in the text plan (see get_playbook). Searches the curated library of slide design DNA by what a slide must do. Returns up to k short summaries (id, slide type, score, purpose, why it works, the layout's component kinds, impact device if any, style, when to use it), at most one per deck; an impact filter returns few results. Call get_reference with an id for the full layout. Reference, never copy.

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": {
      "purpose": "<purpose>"
    },
    "name": "find_references"
  }
}

Input Schema

Name	Required	Description
`k`	No	How many results, 1 to 8 (default 8).
`style`	No	Only slides from decks with this overall look.
`impact`	No	Only impact slides of this kind: how reference decks repeat a slide for effect. Use it when the user wants to emphasize or land a key point: shade_ribbon (the previous slide dimmed, a ribbon stating the takeaway), spotlight (one part highlighted), build (revealed step by step), repeat (an earlier slide brought back as a recap). Few exist.
`purpose`	Yes	What the slide must achieve, in plain words.
`industry`	No
`data_type`	No
`slide_type`	No	Archetype id (see the archetypes stage of get_playbook).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already establish a safe, closed-world read, and the description layers on real behavior beyond them: result cap of k, at most one result per deck, a warning that an impact filter yields few results, the full shape of each returned summary, and a usage norm ("Reference, never copy"). Those constraints materially change how an agent should call and interpret it.

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 trigger and the core action, then the return shape, then the routing hint. The parenthetical field list is dense but justified because no output schema exists; a couple of clauses ("Reference, never copy") sit at the tail where they are easy to miss.

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 responsibly enumerates the returned fields, plus sparsity caveats and the follow-up tool, which is enough to call it correctly. The one gap is how the required free-text purpose is matched against the library, which an agent must guess at.

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 71% and the enums are self-documenting, so the schema carries most of the load. The description still adds meaning the schema does not: k is framed against the one-result-per-deck rule, and the impact parameter is flagged as producing sparse results, which is not visible in the enum itself.

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: searches a curated library of slide design DNA by what a slide must do. It also distinguishes itself from siblings by name — get_playbook for the plan stage and get_reference for the full layout behind an id — so an agent can route without opening a 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?

Gives a clear precondition ("after the slide's claim is settled") and an explicit alternative for the follow-up step ("Call get_reference with an id for the full layout"). It stops short of naming when not to use it, e.g. whether it can be called before the claim is settled, but the timing guidance is unusually concrete.

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

All eightytwenty tools Inspect

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.