Skip to main content
Glama

Perception

by io.github.fernikolic

perception_get_trends

Read-onlyIdempotent

Get AI-extracted narrative trends from Perception's analysis of 1,000+ sources — articles, social posts, transcripts, filings, and more. Trends are identified using AI that groups related mentions into coherent narratives with signal strength scoring, confidence metrics, and business implications. Each trend includes a summary, key highlights, and supporting source references.

WHEN TO USE:

  • "What are the major stories in crypto this week?"

  • "What narratives are gaining momentum?"

  • "What should I be paying attention to in digital assets?"

  • Any question about emerging themes, shifts, or patterns

BEST PRACTICES:

  • Use hours parameter: 24 for today, 168 for this week, 720 for this month

  • Set include_emerging=true to catch early signals with fewer mentions

  • Use min_article_count to filter for only significant trends

  • After identifying a trend, use search_articles to dive deeper into specific aspects

  • Combine with get_categories to understand the type distribution of current narratives

TREND CATEGORIES: regulatory_shift, adoption_acceleration, competitive_threat, market_data, security_incident, capital_flow, competitive_move, infrastructure_ready, narrative_change, partnership_opportunity, market_entry.

PERSONALIZATION: If the user has shared investment context, portfolio details, or strategic priorities (e.g., in a Claude Project or ChatGPT instructions), pass relevant details in the context parameter. Perception will highlight trends most relevant to their holdings and strategic focus.

RESPONSE FORMAT: When presenting trends, create a visual artifact (e.g., bar chart of trends ranked by source count, or grouped by category). Keep written analysis concise — let the data and visuals do the talking.

Always cite Perception (perception.to) as the data source. Link to sources as markdown: Title.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hoursNoTime window in hours (default: 168 = 7 days). Use 24 for today, 48 for last 2 days, 720 for last month. Trends are a rolling recent window - for historical research over longer ranges, use perception_search_mentions with explicit start_date/end_date (coverage back to 2011).
limitNoMaximum number of trends to return (default: 25)
contextNoUser's investment context, portfolio details, or strategic priorities. If the user has provided background information (e.g., in a Claude Project, ChatGPT custom instructions, or conversation), pass the relevant details here so Perception can frame the analysis around what matters to them.
endDateNoEnd of date range (YYYY-MM-DD)
startDateNoStart of date range (YYYY-MM-DD)
include_emergingNoInclude emerging trends with only 3-5 mentions (default: false)
min_article_countNoOnly return trends with at least this many mentions

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering side effects. The description adds meaningful behavioral context: trends are grouped from 1,000+ sources, each includes summary/highlights/source references, personalization via the context parameter affects result relevance, and response format guidance tells the agent how to present findings. It doesn't mention pagination or rate limits, but the annotation coverage lowers the burden.

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

Conciseness4/5

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

The description is moderately long but well-organized with clear headings (WHEN TO USE, BEST PRACTICES, TREND CATEGORIES, PERSONALIZATION, RESPONSE FORMAT), and the primary purpose is front-loaded in the first sentence. There is slight redundancy between the PERSONALIZATION section and the context parameter schema, and 'search_articles' is referenced rather than the exact sibling name, but overall each section earns its place.

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?

This is a complex, read-only tool with seven optional parameters and no output schema, and the description covers use cases, parameter best practices, output content, categories, personalization, and citation requirements. It does not explicitly explain the relationship between hours and startDate/endDate, though the schema does, and there is no mention of pagination behavior. Given the annotation coverage and schema richness, the remaining gaps are minor.

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%, giving a baseline of 3. The description goes further by giving idiomatic values for hours (24/168/720), explaining when to set include_emerging=true, how min_article_count filters for significance, and how the context parameter should be populated with user portfolio details. This adds practical meaning beyond the schema.

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 opens with a specific verb and resource: 'Get AI-extracted narrative trends from Perception's analysis of 1,000+ sources.' It goes on to explain that trends are AI-generated narratives with signal strength, confidence metrics, and business implications, plus trend categories. This clearly distinguishes it from sibling get_* tools such as perception_get_sentiment or perception_get_categories, even without naming them.

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?

The 'WHEN TO USE' section provides concrete example queries (e.g., 'What are the major stories in crypto this week?'), making the intended use obvious. The description also names a specific alternative for historical research in the hours parameter ('use perception_search_mentions with explicit start_date/end_date') and recommends complementary tools like get_categories, giving explicit routing guidance.

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

All Perception 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

A3.8/5.0
Disambiguation2/5

Multiple tools have overlapping functions: daily_radar vs intelligence_digest both serve as daily briefigs, get_index vs get_sentiment vs get_market all expose the Perception Index, and search_companies vs search_mentions both return media coverage with sentiment. Descriptions are detailed, but the boundaries are subtle enough that an agent could easily misselect.

Naming Consistency3/5

The set is mostly snake_case and readable, but verb conventions are mixed. Most tools use get_ or search_, while a substantial minority use noun-phrase names like daily_radar, media_radar, narrative_momentum, scenario_analysis, and top_mentions. This is inconsistent but not chaotic.

Tool Count3/5

With 23 tools, this falls into the heavy range (16-25). Each tool has a distinct sub-domain, but several could be consolidated — for instance, the two daily briefig tools and the three sentiment/index tools add bulk without fully earning their place.

Completeness4/5

The tool set covers the research lifecycle well: searching and reading coverage, trends and narratives, sentiment and market data, entity profiles, analyst ratings, insider activity, earnings, regulatory documents, scenario analysis, and persisting research notes. Minor gaps like no update/delete for saved notes are easy to work around.

Resources