Perception

perception_get_index

Read-onlyIdempotent

Get Perception's five proprietary products and six canonical readings. Responses lead with the API-authored answer, meanings, evidence, freshness, and methodology.

PRODUCT QUESTIONS:

perception: How positive or negative is digital-asset coverage right now compared with its recent norm?
dominance: Which assets own the crypto conversation?
cost_basis: Did Bitcoin's latest complete daily close finish above or below its attention-weighted reference price?
consensus: How aligned are professional groups in their view of Bitcoin?
reach: How broadly is elevated Bitcoin attention appearing across sources, professional groups, publishers, authors, and countries?

HOW TO READ THEM:

A Perception score of 50 means the usual source-by-source tone. Higher and lower readings compare current coverage with each source's own norm.
Narrative Dominance compares the share of tracked-asset conversation across the full asset universe. Former Bitcoin-only dominance clients should use metric=attention_share.
Narrative Cost Basis is an attention-weighted Bitcoin reference price.
Narrative Consensus reads in the agreement direction: a higher score means professional groups are more aligned.
Narrative Reach measures elevated reach versus history across independent coverage panels.
metric=all returns all five product groups and six readings. conviction_gap and breadth remain supported aliases for consensus and reach.

PERCEPTION SCOPES:

market (default) covers the digital-asset corpus on a 24-hour window.
bitcoin covers Bitcoin coverage on a 24-hour window.
ethereum covers Ethereum coverage on a 7-day window and should be compared with that different measurement period in mind.

The optional context can guide follow-up suggestions. Canonical answer text always comes from the API response. Always cite Perception (perception.to) as the data source. Public APIs: api.perception.to/index, api.perception.to/indices, and api.perception.to/indices/dominance.

Input Schema

TableJSON Schema

Name	Required	Description
`date`	No	Specific date to query (YYYY-MM-DD format). Defaults to current/latest.
`scope`	No	Which index to read. 'market' (default) scores the whole digital-asset corpus on a 24h window. 'bitcoin' scores Bitcoin coverage only, 24h. 'ethereum' scores Ethereum coverage only on a 7-DAY window — do not compare it like-for-like against the 24h indexes.
`metric`	No	Product to retrieve. Defaults to perception. dominance is the multi-asset product; use attention_share for the narrower Bitcoin-only equal-source reading.
`context`	No	Optional context for suggested follow-ups only. It never changes the API-authored interpretation.
`include_history`	No	Include bounded history. Sent explicitly on every portfolio and Narrative Dominance request.
`dominance_window`	No	Narrative Dominance range. Applies only to dominance and all; defaults to 1y.
`dominance_granularity`	No	Narrative Dominance bucket size. Applies only to dominance and all; defaults to weekly.

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavioral context: response format ('Responses lead with the API-authored answer, meanings, evidence, freshness, and methodology'), the context parameter's behavior ('It never changes the API-authored interpretation'), the citation requirement, and public API endpoints. No contradiction.

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 long but well-structured with scoped sections and bullets: product questions, how-to-read instructions, scopes, and endpoint citations. Each section carries needed decision information, and the response-format statement is front-loaded.

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 read-only 7-parameter tool with no output schema, the description covers return shape, metric semantics, scopes, aliases, citation, and API endpoints. An agent has enough to invoke it correctly without needing an example.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description goes beyond field names: it explains how to read each metric (e.g., 'Narrative Consensus reads in the agreement direction' and 'Narrative Reach measures elevated reach versus history'), clarifies aliases, and gives scope windows. This exceeds the baseline for schema-covered parameters.

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: 'Get Perception's five proprietary products and six canonical readings,' then enumerates the product questions, so an agent knows this tool returns Perception index readings. It does not explicitly contrast itself with sibling tools like perception_get_sentiment, but the product/reading vocabulary is distinctive enough to identify the index tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear internal guidance on scope and metric selection, e.g., 'ethereum covers Ethereum coverage on a 7-day window and should be compared with that different measurement period in mind' and 'Former Bitcoin-only dominance clients should use metric=attention_share.' However, it never says when to choose this tool over an alternative tool, leaving tool-vs-sibling routing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Perception tools Inspect

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

Need Help?