Skip to main content
Glama

Perception

by io.github.fernikolic

perception_search_companies

Read-onlyIdempotent

Search for media coverage of a specific company using entity-recognition powered matching. Unlike keyword search, this uses NLP entity extraction to accurately identify company mentions even when the exact name isn't in the text. Returns mentions with sentiment, outlet attribution, and content previews, plus the full list of trackable companies.

WHEN TO USE:

  • "What is the media saying about Coinbase?"

  • "How is BitGo covered in the press?"

  • "Compare media perception of Company A vs Company B"

  • Due diligence media scans for investment or partnership decisions

BEST PRACTICES:

  • Use exact company names for best NLP matching

  • Combine with get_sentiment for market-wide context alongside company-specific coverage

  • Run the same company across different date ranges to track perception changes over time

  • Cross-reference with get_trends to see if company coverage aligns with broader narrative themes

RESPONSE FORMAT: When presenting company coverage, create a visual artifact (e.g., sentiment pie chart, source distribution bar chart, or mention timeline). Keep written analysis concise — let the data and visuals do the talking.

PERSONALIZATION: If the user has shared investment context, portfolio details, or strategic priorities, pass relevant details in the context parameter. Perception will frame company coverage around what matters to them.

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

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of mentions to return (default: 50, max: 200)
companyYesCompany name to search for (e.g., 'BitGo', 'Coinbase', 'MicroStrategy', 'Tether'). Uses entity-recognition matching, so exact name works best.
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.
startDateNoStart date for search range (YYYY-MM-DD). Defaults to 30 days ago.

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds meaningful behavioral detail: NLP entity extraction, return contents such as sentiment, outlet attribution, content previews, and the full list of trackable companies, plus presentation and citation expectations.

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 long but well organized into targeted sections: WHEN TO USE, BEST PRACTICES, RESPONSE FORMAT, and PERSONALIZATION. Core behavior is front-loaded, and most content earns its place, though some best-practice bullets are slightly redundant.

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?

With no output schema, the description compensates by listing what the tool returns, how to present results visually, and how to cite and link mentions. It covers use cases, personalization, and response expectations, leaving little ambiguity for an agent to invoke the tool correctly.

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?

Schema description coverage is 100%, so the schema already documents all five parameters. The description adds useful practical guidance on exact company names, date-range tracking, and context personalization, but does not substantially redefine parameter semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

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: 'Search for media coverage of a specific company using entity-recognition powered matching.' It also contrasts with keyword search, which helps differentiate the tool, though it does not explicitly name a sibling such as perception_search_mentions.

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?

A dedicated 'WHEN TO USE' section lists concrete user queries and due-diligence scenarios, and 'BEST PRACTICES' recommends pairing with get_sentiment and get_trends. It provides clear contexts but no explicit when-not-to-use guidance or named alternative tools for exclusions.

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