Skip to main content
Glama

HALO Homebridge AI Surfaces

Display live Homebridge product media

display_homebridge_product_media
Read-onlyIdempotent

Render the final HALO product-media card only when the buyer explicitly requested additional images, videos, or a media gallery and get_homebridge_product_media was just called. Pass the same category, product handle, exact SKU, requested media types, and limit. Prefer the returned native image content; never convert its image or Markdown fallback to raw HTML. NEVER call this after configure_homebridge_fire_pit merely to display the resolved product, because the configurator already renders that exact card; doing so would create a duplicate card. This read-only presentation tool retrieves the authoritative Shopify media snapshot and creates no cart, checkout, order, or payment.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
skuNo
limitNo
categoryYes
mediaTypesNo
productHandleYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
mediaYes
productYes
boundariesYes
mediaCountYes
generatedAtYes
schemaVersionYes
dataProvenanceYes
selectedVariantYes
requestedMediaTypesYes

TDQS

A4.3/5.0
Behavior4/5

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

The description reinforces the readOnlyHint and idempotentHint by stating it's a 'read-only presentation tool' and 'creates no cart, checkout, order, or payment.' It adds a specific behavioral warning about not converting image or Markdown fallback to raw HTML, which is beyond the annotations.

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?

The description is a single, well-structured paragraph that front-loads the primary purpose and then adds conditions and warnings. Each sentence adds value (e.g., the negative usage case), and there is no redundancy or fluff.

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 that an output schema exists and this is a presentation tool, the description adequately covers the calling context: when to call, what to pass, and what it produces (a rendered card). It also warns about duplication and read-only nature, making it complete for an agent to safely invoke.

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?

The description mentions all five parameters by name ('same category, product handle, exact SKU, requested media types, and limit') and implies they must match the retrieval call, but provides little additional semantic detail beyond the schema's enums and defaults. It does clarify 'exact SKU' meaning consistency, but this is minimal.

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 a specific verb ('render') and resource ('final HALO product-media card'), and distinguishes it from retrieval (get_homebridge_product_media) and configuration (configure_homebridge_fire_pit). It even names the sibling tool it is not.

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?

It provides explicit conditions for use ('only when the buyer explicitly requested additional images... and get_homebridge_product_media was just called') and explicit when-not-to-use ('NEVER call this after configure_homebridge_fire_pit merely to display the resolved product...'). It also points to the alternative tool and the reason (duplicate card).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation3/5

Several tools cluster around similar actions: category listing vs. per-category catalog, media retrieval vs. media display, and fire-pit configuration vs. major-variant resolution. The long guardrail descriptions help, but an agent could easily misselect without reading them carefully.

Naming Consistency4/5

Tool names are consistently snake_case verb_noun with a homebridge domain prefix, and verbs like get, list, configure, resolve, qualify, and prepare clearly signal actions. Minor inconsistencies exist, such as mixing list and get for read operations and using get_halo_connection_status instead of the usual homebridge prefix.

Tool Count5/5

Ten tools fit the browse-qualify-resolve-media-checkout workflow without feeling bloated. Each tool serves a distinct phase or role in the buyer journey, from connection status and category discovery to exact variant resolution and checkout handoff.

Completeness4/5

The server covers the full buyer journey for its stated domain: discover categories, qualify fire-pit choices, resolve exact variants, retrieve and display media, and prepare checkout. Minor gaps exist, such as no broad product search or cart/order management, but those appear intentionally out of scope for this Shopify handoff server.

Resources