Skip to main content
Glama

Perception

by io.github.fernikolic

perception_get_capital_exposure

Read-onlyIdempotent

Get the institutional capital picture for a US-listed company: SEC 13F institutional holders with quarter-over-quarter flow (net shares added or cut, new positions, exits), 13D/G beneficial owners above 5%, and self-reported Bitcoin treasury holdings where they exist.

WHEN TO USE:

  • "Who owns MSTR institutionally and are they adding or cutting?"

  • "How much Bitcoin does this company hold on its balance sheet?"

  • "Did institutions enter or exit this name last quarter?"

  • Pairing capital behavior against media coverage (use perception_get_entity_profile or perception_get_divergences for the narrative side)

WHAT IT REPORTS: Reported facts only. 13F holdings are quarterly filings with up to a 45-day lag, so this is the most recently REPORTED position, never the live one. The QoQ flow summary is computed across all filers, so the headline (net shares, new positions, exits) covers the full institutional base rather than only the visible top holders. Treasury data comes from self-reported public disclosures (CoinGecko aggregation). No claims about future prices.

BEST PRACTICES:

  • Say "as of {quarter}" when citing 13F numbers; the lag matters

  • Follow up with perception_get_insider_activity for the discretionary (Form 4) view, which is far fresher

  • Follow up with perception_narrative_momentum or perception_get_entity_profile to compare capital behavior with coverage direction

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

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tickerYesStock ticker symbol (e.g., MSTR, COIN, MARA, SMLR). Must be a US-listed ticker.
contextNoUser's investment context, portfolio details, or strategic priorities so the capital picture can be framed around what matters to them.

TDQS

A4.7/5.0
Behavior5/5

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

Even though annotations already mark this as a read-only, idempotent, non-destructive operation, the description adds significant behavioral context: 13F data lags up to 45 days, figures are the most recently reported rather than live, QoQ flow is computed across all filers, Bitcoin treasury data is self-reported, and no future price claims are made. This goes well 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.

Conciseness5/5

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

The description is longer than typical but well structured with clear sections: overview, when to use, what it reports, and best practices. Every sentence carries useful information for invocation or interpretation, and the core purpose is front-loaded. There is no filler or redundancy.

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?

With no output schema, the description does the necessary work of explaining what the tool returns: institutional holders, flow summary, beneficial owners, and treasury holdings. It also covers important caveats about data freshness and source reliability, making the tool's behavior fully understandable to an agent.

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 explains both ticker and context parameters. The description reinforces that the tool applies to US-listed companies and that context is used for framing, but it does not add new parameter-level semantics beyond the schema. 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 opens with a specific verb and resource: 'Get the institutional capital picture for a US-listed company,' then enumerates exactly what is included (13F holders, QoQ flow, 13D/G owners, Bitcoin treasury holdings). This clearly differentiates it from narrative or sentiment siblings like perception_get_sentiment or perception_narrative_momentum.

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 gives concrete example queries and explicitly routes the agent to alternatives: perception_get_entity_profile or perception_get_divergences for the narrative side, and perception_get_insider_activity for a fresher discretionary view. This is explicit when-to-use and when-not-to-use 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