Skip to main content
Glama
prismicio

@prismicio/mcp-server

Official
by prismicio

how_to_model_slice

Get step-by-step guidance to create or update Prismic slice models using best practices. Input slice details and content requirements to receive naming conventions, field shapes, and validation steps.

Instructions

PURPOSE: Provide detailed, opinionated guidance to create or update Prismic slice model files using modern best practices, including naming, file placement, allowed fields, shapes, and configuration.

USAGE: Use FIRST for any Prismic slice creation or modeling request. Do not use for component or mock implementation. Input Type Selection Rules:

  • If the user attaches an image, include "image".

  • If the user attaches code, include "code".

  • Include "text" ONLY if the prompt contains model-related information (e.g., explicitly describes desired fields/structure, adds nuance, or overrides what is seen in the code/image).

  • It is acceptable to include multiple input types when each adds model-relevant signal per the rules above.

RETURNS: Step-by-step modeling instructions, naming conventions, final Prismic model shapes, comprehensive field shape reference, opinionated modeling guidance, validation and testing steps.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sliceMachineConfigAbsolutePathYesAbsolute path to 'slicemachine.config.json' file
sliceNameYesThe name of the slice, it MUST be PascalCase, e.g., 'SliceName', cannot start with a number, and with no special characters allowed
isNewSliceYesWhether this is a new slice creation (true) or updating existing slice (false)
contentRequirementsYesDescription of what content the slice should contain (e.g., 'hero with title, description, and CTA button')
inputTypesYesThe kinds of input present in the prompt.
Behavior4/5

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

No annotations provided, so description carries full burden. It clearly states it returns step-by-step guidance, naming conventions, shapes, etc. It does not mention side effects, but as a guidance-only tool, that's acceptable. Could be more explicit about not making changes.

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?

Well-structured with sections (PURPOSE, USAGE, Input Type Selection Rules, RETURNS) and bold headings. Concise but informative; each sentence adds value. Could be slightly more streamlined.

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?

Given no output schema, the description covers purpose, usage, parameter guidance, and return value. It's adequate for an AI agent to select and invoke correctly. Missing only explicit mention that it does not modify anything, but implied.

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 100% with good descriptions. The description adds extra meaning: explains input type selection rules, gives an example for contentRequirements, and reinforces the PascalCase pattern for sliceName. This adds significant value beyond schema.

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?

The description clearly states the purpose: providing opinionated guidance for Prismic slice model files. It specifies the resource (slice model files) and action (create or update), and distinguishes from sibling tools like how_to_code_slice and how_to_mock_slice.

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?

Explicitly states 'Use FIRST for any Prismic slice creation or modeling request' and 'Do not use for component or mock implementation.' Provides detailed input type selection rules, giving clear context on when to include each input type.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/prismicio/prismic-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server