Skip to main content
Glama

Trillboards DOOH Advertising

find_similar_moments

Find historically similar audience moments across the screen network using embedding similarity search. Input a natural-language description of the target moment.

Moment embeddings are 768-D vectors generated from multi-modal observation data (visual, audio, environmental, social) via the MomentEmbeddingService. This tool embeds your query text and finds the closest real-world moments via approximate nearest-neighbour (ANN) cosine similarity over a Lance IVF_PQ index.

CONSISTENCY: results are APPROXIMATE and EVENTUALLY CONSISTENT.

  • Approximate: retrieval is ANN, not an exhaustive scan (measured recall ~0.96 against exact KNN), so an identical query may omit a borderline match.

  • Eventually consistent: the index is served from a replicated pool whose replicas refresh independently, so for up to 5 minutes after new moments are published, two identical calls may return slightly different result sets. The difference is confined to the VISIBILITY of newly-published moments; the relative ranking of already-visible ones does not change. Do not use this tool where a repeatable, exhaustive result set is required.

WHEN TO USE:

  • Searching for historical moments similar to a target scenario

  • Finding "moments like this one" across different venues/times

  • Discovering when similar audience compositions or behaviors occurred

  • Planning ad placements based on past similar contexts

RETURNS:

  • data: Array of matching observations with similarity scores

    • observation_id, observed_at, venue_type, device_id, screen_mongo_id

    • payload: full observation data

    • evidence_grade: quality of observation

    • similarity: cosine similarity score (0-1, higher = more similar)

  • metadata: { result_count, embedding_model, min_similarity_threshold }

  • suggested_next_queries: Follow-up queries

EXAMPLE: User: "Find moments with high engagement in evening restaurants with families" find_similar_moments({ query: "evening restaurant venue with families present, high emotional engagement and attention" })

User: "When did we see young adults highly engaged at transit screens?" find_similar_moments({ query: "transit venue morning commute young adults high attention" })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum results to return. Default: 10, max: 200.
queryYesNatural-language description of the target moment. Be descriptive about venue, time, audience, behavior, and conditions.
venue_typeNoFilter results to a specific venue type. Optional.
min_similarityNoMinimum cosine similarity threshold (0-1). Default: 0.7. Lower values return more but less relevant results.

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations provided, the description carries full burden. It thoroughly discloses the approximate nature (ANN, recall ~0.96), eventual consistency (replicated pool, up to 5 minutes visibility differences), and what remains stable (relative ranking of already-visible moments). This is exemplary behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Although relatively long, the description is well-structured with clear sections (intro, background, CONSISTENCY, WHEN TO USE, RETURNS, EXAMPLE). Every section earns its place, providing necessary technical context without redundancy. Front-loading the main purpose makes it immediately usable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of embedding-based search with ANN and eventual consistency, and the absence of an output schema, the description fully covers the return format (data, metadata, suggested_next_queries), the consistency caveats, and practical usage examples. It is complete enough for an agent to invoke the tool correctly and interpret results.

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%, so baseline is 3. The description adds value with examples showing how to phrase the query for different scenarios, which illustrates query semantics beyond the schema. However, it does not elaborate on limit or venue_type beyond what the schema already states.

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?

Description begins with a specific verb+resource+method: 'Find historically similar audience moments across the screen network using embedding similarity search.' It clearly distinguishes the tool from exact query tools (like query_observations) and other semantic search tools by emphasizing the embedding-based ANN approach.

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?

A dedicated 'WHEN TO USE' section lists four concrete scenarios, and an explicit exclusion states: 'Do not use this tool where a repeatable, exhaustive result set is required.' This gives clear guidance on when to choose this tool over alternatives.

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

B3.3/5.0
Disambiguation2/5

There are exact duplicates (get_task_status/tasks_get, list_tasks/tasks_list) and several overlapping analytics, attribution, and semantic search clusters (get_attention_metrics vs get_creative_attention vs get_social_attention; find_similar_moments vs semantic_search_observations; get_campaign_attribution vs get_multi_touch_attribution vs get_roas). Detailed descriptions help, but with 83 tools an agent will frequently struggle to pick the right one.

Naming Consistency3/5

Most tools follow a snake_case verb_noun pattern (list_devices, create_campaign, delete_webhook), but there are notable inconsistencies: list_* and get_* are used interchangeably for list operations, attention tools mix conventions (get_attention_metrics vs get_creative_attention vs get_social_attention), and the legacy tasks_get/tasks_list names break the established get_task_status/list_tasks pattern.

Tool Count1/5

83 tools is an extreme count for a single MCP server, spanning device management, sensing, campaigns, media buys, attribution, webhooks, billing, API discovery, and AdCP protocol concerns. This is a broad API surface dump rather than a focused tool set, and it would be far better split into several coherent servers.

Completeness2/5

Despite the enormous surface, core campaign lifecycle is incomplete: create_campaign explicitly tells the agent to use update_campaign to activate a campaign, but no update_campaign tool exists, and there are no list/delete campaign tools. Significant capabilities exist for analytics, attribution, and webhooks, but the primary advertising workflow has a dead end.

Resources