Skip to main content
Glama

Perception

by io.github.fernikolic

perception_search_mentions

Read-onlyIdempotent

Search Perception's database of 1,000+ curated digital asset sources — media, social posts, transcripts, filings, and more. Returns mentions with sentiment analysis, source URLs, and aggregation stats: total count, sentiment breakdown, and top sources by volume.

QUERY SYNTAX:

  • Commas = OR logic: "Tether, USDT" finds either term

  • Spaces = AND logic: "Circle regulation" requires both

  • Filter by sentiment (Positive/Negative/Neutral), outlet, date range, language, or region

  • Omit query to get recent mentions across all topics

LANGUAGE & REGION FILTERS:

  • language: Filter by language — ISO 639-1 codes (e.g., "de" for German, "pt" for Portuguese). Essential for capturing region-specific regulatory terminology.

  • region: Filter by where events are happening (e.g., "Europe", "Latin America"). Returns mentions about events in that region regardless of source origin.

  • region_outlet: Filter by source's home country/region (e.g., "Europe" = European digital asset media only).

WHEN TO USE:

  • "What is the media saying about Bitcoin ETFs?"

  • "Show me negative coverage of stablecoins in the last 30 days"

  • "What are German-language sources saying about custody regulation?" → use language: "de"

  • Competitive media analysis, narrative tracking, newsjacking research

BEST PRACTICES:

  • Start broad, then narrow with filters if too many mentions

  • Combine with get_trends to understand narrative context around search results

  • Combine with search_companies for entity-specific analysis (more accurate than keyword search for company names)

  • Use sentiment filter to isolate critics or advocates

  • region (where story is about) ≠ region_outlet (where media is from) — use both together for most precise geographic analysis

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 frame results around what matters to them — for example, highlighting mentions that affect their holdings or strategic focus.

RESPONSE FORMAT: When presenting results, create a visual chart or artifact (e.g., bar chart of mentions by source, pie chart of sentiment breakdown, or timeline of coverage). Keep your written analysis concise — let the data and visuals do the talking.

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

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoSearch query. Use commas for OR logic (e.g., 'Circle, USDC'), spaces for AND logic (e.g., 'Circle regulation'). Searches across titles and full content. Optional — omit to get recent coverage.
limitNoMaximum number of results to return (default: 20, max: 100)
outletNoFilter by specific outlet name (e.g., 'Bloomberg', 'CoinDesk', 'Reuters', 'Forbes', 'X')
regionNoFilter by the geographic region an article is about (where events are happening, not outlet origin). Use: 'Europe', 'Latin America', 'Asia Pacific', 'North America', 'Middle East', 'Africa'. Maps to Perception's primary_country field. Use region_outlet to filter by where the publishing outlet is based.
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 date for search range (YYYY-MM-DD). Defaults to today.
languageNoFilter by article language using ISO 639-1 codes. Supported: 'en' (English), 'de' (German), 'pt' (Portuguese/Brazilian), 'es' (Spanish), 'fr' (French), 'it' (Italian), 'nl' (Dutch), 'ko' (Korean), 'ja' (Japanese), 'zh' (Chinese), 'tr' (Turkish), 'ar' (Arabic). Returns only articles from outlets publishing in that language. Ignored when 'outlet' is also specified.
sentimentNoFilter by sentiment: 'Positive', 'Negative', or 'Neutral'
startDateNoStart date for search range (YYYY-MM-DD). Defaults to 7 days ago.
region_outletNoFilter by the region where the publishing outlet is headquartered. Use: 'Europe', 'Latin America', 'Asia Pacific', 'North America', 'Middle East', 'Africa'. Returns articles from media outlets based in that region. Ignored when 'outlet' is also specified.

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already mark it read-only and idempotent; the description adds valuable behavioral context: query syntax semantics, region vs. region_outlet distinction, aggregation stats returned, and explicit response-format expectations (visual chart, citation, markdown links). This tells the agent what executing the tool will and will not produce beyond the safe-read 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 longer than average but earns its length: it is front-loaded with the core purpose and uses clear headings so an agent can scan to the relevant section. There is no filler or repetition of schema text; each section addresses a distinct decision or behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter read-only search tool with no output schema, this is complete: it covers when to use it, query syntax, all filter classes, output contents, output formatting, and cross-tool guidance. The only gaps (e.g., ignored language when outlet is specified) are already covered by the input schema.

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 coverage is 100%, so the baseline is high; the description still adds meaning by explaining comma/space query semantics, examples for language codes, the important region vs. region_outlet distinction, and how `context` personalizes results. Not every parameter gets extra prose, but the most semantically subtle ones are enriched.

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?

Opens with a specific verb+resource: 'Search Perception's database of 1,000+ curated digital asset sources' and names the returned payload (mentions with sentiment, source URLs, aggregation stats). This distinguishes it from sibling search tools like search_companies and search_regulatory by focusing on media mentions and their analytics.

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?

Has an explicit 'WHEN TO USE' section with concrete example queries and use cases, plus 'BEST PRACTICES' that name sibling tools (get_trends, search_companies) and explain when to prefer them. It even gives routing criteria such as using search_companies for entity-specific analysis because it is 'more accurate than keyword search for company names'.

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