api_searchGoogle web search. ?q=query&num=5 returns organic results with title, link, snippet. [HTTP x402 price: $0.002]
| Name | Required | Description | Default |
|---|---|---|---|
| params | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / params / additionalPropertiesRemoved value: -trueInput schema / properties / params / propertiesAdded value: +{
+ "num": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ },
+ "q": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+ }
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description must carry the behavioral disclosure burden. It does add useful context by mentioning the cost ($0.002) and the result shape (organic results with title, link, snippet). However, it omits potential rate limits, error behavior, whether the query uses live data, and other operational constraints that would matter when selecting or invoking the tool.
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 short, direct, and front-loaded with the core purpose ('Google web search'). It packs usage syntax, output shape, and cost into one compact block with no filler.
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?
For a simple search tool, the description covers invocation and output reasonably well, and an output schema exists for return values. However, without any sibling differentiation or explicit parameter behavior (e.g., num limits, optional/required q), the description is not fully complete for confident tool selection and invocation.
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?
The schema has 0% description coverage, so the query-string example compensates: '?q=query&num=5' clearly implies q is the search query and num controls the result count. This is not an exhaustive explanation, but it gives the agent the essential meaning needed to call the tool.
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 states a specific verb and resource: 'Google web search' and what it returns ('organic results with title, link, snippet'). It is clear, but it does not explicitly distinguish itself from sibling tools like api_serp_google, which may serve a similar purpose.
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?
No guidance is provided about when to use this tool versus alternatives such as api_serp_google, api_serp_yandex, or api_scrape. The description implies it is for simple Google organic search results, but it does not state any selection criteria or exclusions.
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.
Several tools have unclear boundaries: api_search and api_serp_google both return Google results, api_scrape and api_render_text both extract page text, and api_hash_multi overlaps with api_sha256 for SHA-256/SHA-512. While many tools are distinct, these overlapping pairs create real misselection risk.
Every tool follows the same api_<snake_case> pattern with no mixed conventions or casing styles. The prefix makes the server immediately recognizable and the action/resource is consistently readable across all 44 tools.
44 tools is well over the 25+ threshold for a well-scoped set, making the server feel like a grab-bag of unrelated utilities. Even though each tool is small and individually useful, the overall surface is too large and would benefit from consolidation into focused sub-servers.
The set covers many common utility categories—encodings, conversions, text analysis, web scraping, SEO, and trends—but has notable one-way gaps: CSV/YAML/TOML all convert to JSON but not back, and markdown converts to HTML but not the reverse. The broad domain makes full completeness hard to define, so only major reverse-conversion gaps stand out.