smarterdeck
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SMARTERDECK_API_KEY | Yes | Your SmarterDeck API key, used as a Bearer token in the Authorization header. Get one at https://smarterdeck.com/dashboard?view=api_keys |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_presentation_suiteA | Genera una suite ejecutiva completa de presentaciones 5-en-1 (PowerPoint editable DrawingML, Presentación Web interactiva, Executive Dashboard de KPIs, Whiteboard Infographic y PDF de alta definición) a partir de cualquier tema de negocios, reporte financiero o datos. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only a single tool, there is no possibility of confusing it with another; the agent has exactly one obvious action to select. The description clearly scopes what the tool produces.
The lone tool name follows a clean snake_case verb_noun convention (generate_presentation_suite) that is descriptive and predictable. There are no competing conventions to clash with.
A single monolithic tool subsuming a 5-in-1 suite (PPT, web deck, dashboard, infographic, PDF) is borderline thin — there is no way to request just one artifact or tweak granular outputs. The count is defensible for a one-shot generator but lacks flexibility.
The tool covers generation of all five advertised artifacts in one call, so the core purpose is met, but there are no follow-up operations (regenerate a single format, edit output, list prior suites, customize templates). Agents have no recovery path if part of the output is wrong.