Skip to main content
Glama

CreativeScope — Mobile Game Ad Creative Intelligence

by ai.creativescope

submit_reference_image_search

Submit a reference-image similarity search as an asynchronous job. Use this when the user provides a directly downloadable public HTTPS image URL. The URL must resolve to image bytes without login or hotlink protection; HTML pages, local paths, and base64 are not supported. The embedding provider validates image format and size asynchronously and returns IMAGE_FETCH_FAILED, INVALID_IMAGE, or EMBEDDING_MODEL_ERROR when processing cannot continue. Genre aliases are normalized internally. If a normalized genre produces no candidates, the completed result explicitly marks a visual-only fallback instead of silently returning an empty set. Example: 'Find ads visually similar to this reference image.'

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
genreNoOptional game genre or sub-genre, for example SLG, match-3, puzzle, RPG. Aliases are normalized internally. If the normalized genre has no candidates, results may use an explicitly disclosed visual-only fallback.
limitNoNumber of similar creatives to return when the job completes. Maximum 20.
formatNoOptional creative format: image, video, or playable.
countryNoOptional ISO 3166-1 alpha-2 country code, for example US, JP, KR, GB.
platformNoOptional platform filter, for example facebook, instagram, tiktok, youtube, admob.
image_urlYesDirectly downloadable public HTTPS image URL. It must return image bytes without login or hotlink protection. Do not pass an HTML page, local path, base64, or expiring authenticated URL.

TDQS

A4.4/5.0
Behavior4/5

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It explains that the job is asynchronous, lists possible error types (IMAGE_FETCH_FAILED, INVALID_IMAGE, EMBEDDING_MODEL_ERROR), and describes genre normalization and visual-only fallback behavior. Missing details like expected latency or polling mechanism, but sufficient for understanding key behaviors.

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?

The description is a single paragraph of four sentences, front-loading the main action and usage context. Every sentence adds value: purpose, usage condition, constraints/failures, and special behavior (fallback). No filler or redundancy.

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 the tool's complexity (async job, multiple failure modes, genre normalization) and no output schema, the description provides sufficient context. It covers input requirements, processing behavior, and fallback logic. It could mention how to retrieve results (sibling tools) but is otherwise complete for a submission tool.

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 description coverage is 100%, so baseline is 3. The description adds meaningful context beyond schema by explaining async processing, failure modes, and fallback behavior. It does not expand on individual parameters beyond what the schema already provides, but enhances overall understanding of parameter usage.

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 action ('Submit a reference-image similarity search') and the resource (asynchronous job). It distinguishes itself from sibling tools like 'get_reference_image_search_results' and 'get_reference_image_search_status' by specifying it is the submission step.

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?

The description provides explicit conditions for use: 'when the user provides a directly downloadable public HTTPS image URL.' It also states what is not supported (HTML pages, local paths, base64). However, it does not mention when to use alternatives like 'find_similar_creatives' or when to avoid this tool.

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

All CreativeScope — Mobile Game Ad Creative Intelligence toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation5/5

Each tool serves a distinct purpose: searching creatives, advertiser profiles, game rankings, image similarity search workflow, etc. Overlaps like find_similar_creatives vs submit_reference_image_search are clearly separated by whether using an existing creative or a new image URL.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (e.g., get_creative_detail, search_advertisers, submit_reference_image_search) with snake_case. No mixed conventions or vague verbs.

Tool Count5/5

12 tools cover the domain of mobile game ad intelligence without redundancy. The count feels appropriate—enough to handle common tasks (search, detail, rankings, image search) without overwhelming.

Completeness5/5

The tool set covers essential workflows: finding creatives via text or image, analyzing advertiser and game rankings, retrieving creative details and insights, and generating briefs. The async image search workflow is fully supported with submit, status, and results tools.

Resources