Skip to main content
Glama

Perception

by io.github.fernikolic

perception_get_earnings_intelligence

Read-onlyIdempotent

Get AI-analyzed earnings call intelligence for a public company. Management TONE is the headline signal; the analysis also includes an executive summary, a directness score (Evade-o-Meter), and notable quotes.

WHEN TO USE:

  • "How did Coinbase's earnings call go?"

  • "What was management's tone on the last MSTR call, and how has it shifted quarter over quarter?"

  • "What did MARA management say about Bitcoin strategy?"

  • "Give me the earnings summary for TSLA"

  • Any question about earnings calls, management tone, executive commentary, or quarterly results

COVERAGE: 50+ crypto/fintech/Bitcoin treasury companies. Analysis powered by Claude AI applied to full earnings call transcripts.

DATA:

  • Management tone classification (e.g., "confident", "cautious", "defensive") - LEAD with this and with its quarter-over-quarter change

  • Executive summary (key points + one-sentence takeaway)

  • Evade-o-Meter directness score (0-100) with classification ("Relatively Direct" to "Highly Evasive")

  • Call participants roster (executives with their stated titles, parsed from the call introductions)

  • Notable quotes with speaker attribution (name plus stated title where verified; "Management" when the individual speaker could not be verified)

HOW TO WEIGH THE TWO SCORES: In Perception's 455-call backtest the numeric directness score showed no relationship with subsequent returns (r about -0.02), while tone cohorts separated meaningfully. Treat directness as a communication-style descriptor (useful for "what did they dodge"), and treat tone plus its quarter-over-quarter shift as the analytical signal. Neither is a forecast.

BEST PRACTICES:

  • Track tone across quarters; a deterioration (e.g. confident to cautious) is the single most useful thing this tool surfaces

  • Combine with get_analyst_ratings to see if analyst sentiment aligns with management tone

  • Use alongside get_insider_activity to compare what management said with what insiders did

PERSONALIZATION: Pass context parameter with portfolio details so Perception can highlight earnings intelligence for companies the user holds.

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

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearNoFiscal year (e.g., 2026). Defaults to the most recent available quarter.
tickerYesStock ticker symbol (e.g., COIN, MSTR, MARA, TSLA, HOOD). Must be a US-listed ticker with earnings coverage.
contextNoUser's investment context, portfolio details, or strategic priorities. Pass relevant details so Perception can frame earnings analysis around what matters to them.
quarterNoFiscal quarter (1-4). Defaults to the most recent available quarter.

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive; the description adds non-obvious behavioral details: data source and construction (Claude AI on full transcripts), coverage constraint (50+ crypto/fintech/Bitcoin treasury companies), reliability caveat for the directness score (r ≈ -0.02 in a 455-call backtest), and citation requirement. This substantially goes beyond 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?

Structured into labeled sections (WHEN TO USE, COVERAGE, DATA, BEST PRACTICES, PERSONALIZATION) with front-loaded purpose. Though longer than minimal examples, every section earns its place by carrying decision-relevant content; there is no filler or tautology.

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?

Despite no output schema, the DATA section enumerates all return components (tone, summary, Evade-o-Meter, participants, quotes) and the HOW-TO-WEIGH section clarifies score interpretation. Combined with coverage, examples, personalization guidance, and citation instruction, nothing critical is missing for an agent to invoke and present results correctly.

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?

Input schema covers 100% of four parameters, so baseline is 3; description adds value for the `context` parameter by explaining to pass portfolio details so Perception can highlight user-relevant intelligence. It also reinforces ticker examples and US-listing coverage, but most parameter semantics remain in 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?

States a specific verb and resource ('Get AI-analyzed earnings call intelligence for a public company') plus headline signal. Describes components and coverage, making it clearly distinct from sibling sentiment/research tools even without an explicit contrast. The name and content align.

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?

Provides a WHEN TO USE section with concrete query examples and a catch-all ('Any question about earnings calls...'). It names complementary tools (get_analyst_ratings, get_insider_activity) in best practices but does not explicitly state when not to use this tool or name a direct alternative, so it stops short of a full 5.

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