Search Ads
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query | |
| budgets | No | Budgets to filter by | |
| formats | No | Formats to filter by | |
| industries | No | Industries to filter by | |
| objectives | No | Objectives to filter by | |
| placements | No | Placements to filter by |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. The phrase 'Search Ads' offers no information about side effects, rate limits, authentication, return structure, or any other behavioral aspect. The agent gets zero transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is only two words, which is under-specification rather than conciseness. It does not structure any useful information for the agent. This is similar to the 'Process' calibration example, scoring low for lack of substance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 6 parameters, no output schema, and no annotations, this tool requires a substantial description to be usable. The two-word description is completely inadequate for the agent to understand what the tool does, what it returns, or how to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The parameter descriptions like 'Search query' and 'Budgets to filter by' are present but minimal; the tool description adds no additional meaning beyond what the schema already provides. A 3 is appropriate because the schema documents all parameters, albeit shallowly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Search Ads' essentially restates the tool name (scrapecreators_search_ads). It indicates a search operation on ads but provides no specific verb+resource detail, such as what kind of ads, what data is returned, or how this differs from sibling tools like scrapecreators_ad_details or scrapecreators_advertiser_search. This is a tautology.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool vs alternatives. The description does not mention any context, prerequisites, or exclusions. Without additional information, an agent cannot determine when this tool is preferred over other search-related tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The tool set has significant overlap and ambiguity, particularly within the 'scrapecreators_' prefix where many tools appear to target similar social media platforms and content types (e.g., 'scrapecreators_posts', 'scrapecreators_posts_get', 'scrapecreators_post', 'scrapecreators_post_get'). Additionally, tools like 'tavily_research' and 'tavily_search' have overlapping purposes with 'web_search_exa', making it difficult for an agent to distinguish when to use each. While some tools like 'get_credits' or 'ideogram_v3' are distinct, the overall set is confusing due to redundant functionalities.
Naming conventions are highly inconsistent across the tool set. There is a mix of snake_case (e.g., 'get_credits'), kebab-case (e.g., 'find-hooks'), and verbose prefixes (e.g., 'scrapecreators_'). The 'scrapecreators_' tools themselves vary in structure, with some using underscores and others not, and there are duplicate names with slight variations (e.g., 'scrapecreators_ad_details' vs. 'scrapecreators_ad_details_get'). This lack of a predictable pattern makes the tool set chaotic and hard to navigate.
With 124 tools, the count is extremely high and inappropriate for the server's purpose, which appears to be marketing and social media data collection. This many tools suggests poor scoping, likely due to redundancy (e.g., multiple scraping tools for similar platforms) and overlapping functionalities. A well-scoped server in this domain should have far fewer tools, typically in the range of 10-30, to avoid overwhelming agents and ensure clarity.
Despite the high tool count and redundancy, the server covers a broad range of marketing-related functions comprehensively. It includes tools for social media hooks, content validation, SEO analysis (e.g., backlinks, keywords), voice archetypes, copywriting frameworks, and extensive scraping across multiple platforms. There are no obvious major gaps for the marketing domain, as it supports data gathering, content creation, and analysis across various networks and metrics, allowing agents to perform core marketing workflows effectively.