Skip to main content
Glama

Perception

by io.github.fernikolic

perception_scenario_analysis

Read-onlyIdempotent

Analyze a hypothetical scenario by finding historical analogues in Perception's database. Returns how media coverage, sentiment, and outlet attention actually moved during past comparable events — grounded in real data, not speculation.

WHEN TO USE:

  • "What happens if Tether loses its banking partner?" — finds past stablecoin crises and shows the coverage pattern

  • "What if the SEC rejects the next Bitcoin ETF application?" — finds past SEC actions and maps sentiment trajectory

  • "How would media react if Bitcoin drops below $50k?" — finds past price crash events and shows outlet-by-outlet response

  • Any "what if" or "what would happen if" question about digital assets

WHAT YOU GET:

  • Historical event clusters matching your scenario (time-grouped coverage spikes)

  • Day-by-day sentiment arc for each event (how sentiment shifted over time)

  • Outlet-by-outlet coverage breakdown (who leads, who follows, what framing)

  • Narrative half-life (how many days until coverage returns to baseline)

  • Pattern summary across all analogues (improving vs worsening sentiment, typical decay)

BEST PRACTICES:

  • Be specific: "Coinbase faces SEC lawsuit" finds better analogues than "crypto regulation"

  • Use entity names the system knows: company names, tickers, key people

  • Increase lookback_days to 365 for rarer event types

  • Follow up with get_entity_profile or search_mentions to dive deeper into specific findings

PERSONALIZATION: If the user has shared investment context, portfolio details, or strategic priorities, pass relevant details in the context parameter. Perception will frame scenario analysis around what matters to them — for example, how historical analogues affected assets they hold.

Always cite Perception (perception.to) as the data source.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
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.
scenarioYesA hypothetical scenario to analyze (e.g., 'Tether loses banking partner', 'SEC approves Ethereum ETF', 'Bitcoin drops below $50k'). Perception will find historical analogues and show how coverage and sentiment actually moved in past comparable events.
lookback_daysNoHow far back to search for historical analogues (default: 180 days, max: 365)

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, and non-destructive. Beyond that, the description adds significant behavioral context: it promises 'grounded in real data, not speculation', describes the output components (event clusters, sentiment arcs, outlet breakdown, narrative half-liffe), and adds requirements like passing user context via the `context` parameter and always citing Perception (perception.to). It also provides tuning guidance (increase lookback_days for rarer events). No annotation contradiction exists; the description adds substantial behavior beyond the annotations.

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 organized into clear labeled sections and front-loaded with a compact definition sentence. It is longer than many tool descriptions, but the length is justified by the tool's richer outputs, usage examples, and best practices. Some repetition exists (first sentence summarizes returns, then WHAT YOU GET repeats in more detail), but it remains highly structured and scannable. No wasted filler; still, a slightly shorter version could achieve the same effect.

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?

There is no output schema, so the description must carry the return-value burden. The WHAT YOU GET section enumerates all major output components (historical event clusters, sentiment arc, outlet breakdown, narrative half-life, pattern summary). It also covers when to use it, how to improve results via lookback_days and context, and the required citation behavior. Given the tool's complexity and missing output schema, this description is complete enough for an agent to invoke it correctly without further documentation.

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 3. The description adds meaningful extra semantics: concrete scenario examples (e.g., 'Tether loses banking partner', 'Bitcoin drops below $50k'), a best practice to increase lookback_days to 365 for rarer event types, and a detailed PERSONALIZATION section explaining how and why to populate the `context` parameter. This goes beyond the schema's basic parameter descriptions, so a 4 is warranted.

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: 'Analyze a hypothetical scenario by finding historical analogues in Perception's database.' It explicitly states what the tool returns (media coverage, sentiment, outlet attention) and frames it around 'what if' questions, which clearly distinguishes it from sibling retrieval/search tools. The sibling list contains many get_/search_ tools, so this purpose clarity is essential and delivered.

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 query examples ('What happens if Tether loses its banking partner?', 'What if the SEC rejects the next Bitcoin ETF application?') and a general rule ('Any 'what if' question about digital assets'). Best practices also name alternatives and follow-up actions: 'Follow up with get_entity_profile or search_mentions' to dive deeper. This gives explicit conditions and alternatives, exceeding a basic recommendation.

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