Skip to main content
Glama

TrendFlow

by dev.mory

Interest by region

get_interest_by_region
Read-only

Break down search interest for one term by geography. Use this when the user asks where something is popular, or wants a regional or city-level comparison. Values are normalized relative interest (0-100 within the result set).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
regionNoCountry code such as "US", "GB", "TH"; a sub-region such as "US-CA"; or a US metro code such as "807". Empty string means worldwide.
keywordYesA search term, or a topic id from search_topics (e.g. "/m/0mkz").
categoryNoGoogle Trends category id to restrict the query to; 0, the default, is every category. Narrowing disambiguates a word with several meanings without needing a topic id.
timeframeNoTime range. A preset, or a custom range as two ISO dates: "2023-01-01 2023-06-30". The range also sets granularity — hourly ranges return minute-level points and "all" returns monthly ones, so a long range cannot show a short spike.
resolutionNoGeographic granularity of the breakdown.
searchPropertyNoWhich Google surface to measure: empty for web search, or images, news, youtube, or froogle (Shopping). These are separate indexes, so values from different properties are not comparable to each other.

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint: true and openWorldHint: true, so safety is covered. The description adds valuable behavioral context beyond annotations: 'Values are normalized relative interest (0-100 within the result set).' This helps interpret results and clarifies scope ('for one term'). No contradiction with annotations.

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 three sentences, each earning its place: action, usage trigger, and value normalization. It is front-loaded with the primary purpose and contains no redundant or filler words. Ideal conciseness for a tool with a rich schema.

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 has 6 parameters, no output schema, and a read-only nature, the description covers the key usage context and result interpretation (normalized 0-100). It could mention the exact return shape (e.g., list of regions with values), but the name and schema provide enough for an agent to infer the output. The description is complete enough for a well-specified tool.

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 input schema provides 100% coverage with descriptions for all 6 parameters, including enums for resolution and searchProperty, and detailed descriptions for region and timeframe. The tool description does not add further parameter-level semantics; it only states scope and normalization. With high schema coverage, baseline 3 is appropriate.

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 starts with a specific verb+resource: 'Break down search interest for one term by geography.' It clearly differentiates from siblings like get_interest_over_time (which focuses on time) and get_related_queries (which focuses on related terms). The phrase 'where something is popular' further reinforces the geography-specific purpose.

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 usage context: 'Use this when the user asks where something is popular, or wants a regional or city-level comparison.' While it does not list exclusions or alternative tools by name, the guidance is clear enough to distinguish from siblings. The absence of named alternatives prevents a 5, but the context is sufficient for selection.

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

All TrendFlow 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

A4.3/5.0
Disambiguation4/5

Each tool targets a distinct Google Trends data type—regional, temporal, related queries, trending now, topic resolution—so agents can usually tell them apart. However, research_trend overlaps with three of the get_* tools by combining their outputs, so it could be selected instead of a specific tool if the agent wants just one slice. Search topics is clearly separate.

Naming Consistency4/5

Four tools consistently use the get_verb_noun pattern (get_interest_over_time, etc.), but research_trend and search_topics deviate with different verbs while still keeping snake_case verb_noun. The pattern is readable but not perfectly uniform.

Tool Count5/5

Six tools is an appropriate number for a Google Trends server, covering the main interest endpoints plus a convenience aggregator and a topic resolver. Not too many, not too few.

Completeness4/5

The server covers the core Google Trends features: time series, regional breakdown, related queries, trending now, and topic resolution. A notable gap is the absence of a related_topics endpoint (topics related to a keyword), which complements related queries. Overall, the surface is fairly complete for typical trend research tasks.

Resources