Equibles

Search SEC Filings

SearchDocuments

Read-only

Search SEC filings and earnings-call transcripts with hybrid keyword and semantic retrieval, or with match 'phrase' for only the excerpts containing an exact phrase. Omit ticker to search every company, or provide one ticker to search only that company. Returns excerpts with document IDs for SearchDocument or ReadDocumentLines. Use excludeTickers and maxResultsPerCompany only for market-wide discovery; use ListFilings to browse filings newest first without a text query.

Input Schema

Name	Required	Description	Default
`match`	No	How the query matches: 'ranked' (default — relevance-ranked keyword and semantic retrieval that broadens to any of the words when results are sparse) or 'phrase' (only excerpts containing the query's words consecutively and in order; case and punctuation are ignored).	ranked
`query`	Yes	Search query — plain keywords or a short natural-language phrase. In ranked mode, when too few excerpts match every word, the search automatically broadens to match any of the words; concise, filing-phrased terms (e.g. 'Data Center revenue') still rank best. In phrase mode, the exact phrase to find.
`ticker`	No	Optional company ticker; a listing outside the US is MIC:TICKER (e.g. XPAR:AIR). Omit to search across all companies.
`endDate`	No	Optional end date filter in YYYY-MM-DD format
`startDate`	No	Optional start date filter in YYYY-MM-DD format
`maxResults`	No	Maximum number of results to return (default: 5, max: 500)
`documentTypes`	No	Optional document types. Accepts registered values such as TenK, TenQ, EightK, TwentyF, SixK, FortyF, Def14A, SOne, or deployment-registered types such as EarningsCallTranscript. SEC form names such as 10-K, DEFA14A, S-3, SC TO-T or NT 10-K are also accepted; an invalid value returns the full accepted list.
`excludeTickers`	No	Optional tickers to exclude from a market-wide search (max 25). Cannot be combined with ticker.
`maxExcerptChars`	No	Maximum characters per excerpt (default: 0 = full excerpt). Set a small value (e.g. 400) for a compact scan across many results; truncated excerpts end with an explicit note.
`maxResultsPerCompany`	No	Maximum results from any single company (default: 0 = unlimited). Set a small value (e.g. 2) to spread results across more companies for discovery-style queries.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 16, 2026

changedInput schema / properties / ticker / description

Previous value: -"Optional company ticker. Omit to search across all companies."New value: +"Optional company ticker; a listing outside the US is MIC:TICKER (e.g. XPAR:AIR). Omit to search across all companies."

Changed1 schema field changedOct 14, 2026

changedInput schema / properties / documentTypes / description

Previous value: -"Optional document types. Accepts registered values such as TenK, TenQ, EightK, TwentyF, SixK, FortyF, or deployment-registered types such as EarningsCallTranscript. Display names such as 10-K are also accepted; an invalid value returns the full accepted list."New value: +"Optional document types. Accepts registered values such as TenK, TenQ, EightK, TwentyF, SixK, FortyF, Def14A, SOne, or deployment-registered types such as EarningsCallTranscript. SEC form names such as 10-K, DEFA14A, S-3, SC TO-T or NT 10-K are also accepted; an invalid value returns the full accepted list."

Changed2 schema fields changedOct 14, 2026

addedInput schema / properties / match

Added value: +{
+  "default": "ranked",
+  "description": "How the query matches: 'ranked' (default — relevance-ranked keyword and semantic retrieval that broadens to any of the words when results are sparse) or 'phrase' (only excerpts containing the query's words consecutively and in order; case and punctuation are ignored).",
+  "type": "string"
+}

changedInput schema / properties / query / description

Previous value: -"Search query — plain keywords or a short natural-language phrase. When too few excerpts match every word, the search automatically broadens to match any of the words; concise, filing-phrased terms (e.g. 'Data Center revenue') still rank best."New value: +"Search query — plain keywords or a short natural-language phrase. In ranked mode, when too few excerpts match every word, the search automatically broadens to match any of the words; concise, filing-phrased terms (e.g. 'Data Center revenue') still rank best. In phrase mode, the exact phrase to find."

Changed7 schema fields changedAug 27, 2026

removedInput schema / properties / documentType

Removed value: -{
-  "default": null,
-  "description": "Document type filter — one value or a comma-separated list (e.g. 'TenK,TenQ'). Accepts registered type values — 'TenK', 'TenQ', 'EightK', 'TenKa', 'TenQa', 'EightKa', 'TwentyF', 'SixK', 'FortyF', 'TwentyFa', 'SixKa', or 'FortyFa' — or display names (e.g. '10-K', '20-F/A'), plus any deployment-registered type, such as EarningsCallTranscript (display name: Earnings Call) for earnings-call transcripts where available. An unrecognized value returns an error listing every accepted value.",
-  "type": "string"
-}

addedInput schema / properties / documentTypes

Added value: +{
+  "default": null,
+  "description": "Optional document types. Accepts registered values such as TenK, TenQ, EightK, TwentyF, SixK, FortyF, or deployment-registered types such as EarningsCallTranscript. Display names such as 10-K are also accepted; an invalid value returns the full accepted list.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

changedInput schema / properties / excludeTickers / description

Previous value: -"Tickers whose filings are excluded from the results — one value or a comma-separated list (e.g. 'AAPL,MSFT'). Use when a company's own filings would dominate the results for a query about its market."New value: +"Optional tickers to exclude from a market-wide search (max 25). Cannot be combined with ticker."

addedInput schema / properties / excludeTickers / items
```
Added value: +{
+  "type": "string"
+}
```
changedInput schema / properties / excludeTickers / type
```
Previous value: -"string"New value: +"array"
```

changedInput schema / properties / maxResults / description

Previous value: -"Maximum number of results to return (default: 5)"New value: +"Maximum number of results to return (default: 5, max: 500)"

addedInput schema / properties / ticker

Added value: +{
+  "default": null,
+  "description": "Optional company ticker. Omit to search across all companies.",
+  "type": "string"
+}

Changed1 schema field changedAug 22, 2026

changedInput schema / properties / documentType / description

Previous value: -"Document type filter — one value or a comma-separated list (e.g. 'TenK,TenQ'). Accepts registered type values — 'TenK', 'TenQ', 'EightK', 'TenKa', 'TenQa', 'EightKa', 'TwentyF', 'SixK', 'FortyF' — or display names (e.g. '10-K', '8-K'), plus any deployment-registered type, such as EarningsCallTranscript (display name: Earnings Call) for earnings-call transcripts where available. An unrecognized value returns an error listing every accepted value."New value: +"Document type filter — one value or a comma-separated list (e.g. 'TenK,TenQ'). Accepts registered type values — 'TenK', 'TenQ', 'EightK', 'TenKa', 'TenQa', 'EightKa', 'TwentyF', 'SixK', 'FortyF', 'TwentyFa', 'SixKa', or 'FortyFa' — or display names (e.g. '10-K', '20-F/A'), plus any deployment-registered type, such as EarningsCallTranscript (display name: Earnings Call) for earnings-call transcripts where available. An unrecognized value returns an error listing every accepted value."

Changed1 schema field changedJul 23, 2026

changedInput schema / properties / query / description

Previous value: -"Search query. Every word must match (AND semantics on the keyword arm), so prefer concise, filing-phrased terms (e.g. 'Data Center revenue') over long natural-language questions."New value: +"Search query — plain keywords or a short natural-language phrase. When too few excerpts match every word, the search automatically broadens to match any of the words; concise, filing-phrased terms (e.g. 'Data Center revenue') still rank best."

First observedJul 19, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: results are excerpts carrying document IDs intended to feed SearchDocument/ReadDocumentLines, and ranked mode auto-broadens to any-word matching when results are sparse. It stops short of noting rate limits or result-count ceilings beyond maxResults.

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?

Three sentences, no filler, and the core capability plus the primary mode/filter distinction is front-loaded before the alternative-tool pointer. Every clause earns its place despite covering ten parameters.

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?

For a ten-parameter, read-only search tool with no output schema and full schema coverage, the description covers purpose, modes, filtering strategy, follow-up chaining and the sibling alternative. It is only marginally short on output shape (excerpt structure, ordering, pagination), which is not fatal given the cheap schema.

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 description coverage is 100%, so the baseline is 3. The description still adds meaning the schema does not: it frames 'match' as an exact-phrase switch vs. ranked retrieval, and states that excludeTickers/maxResultsPerCompany are intended only for market-wide discovery, which the schema's per-field text does not convey.

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 (search), specific resources (SEC filings and earnings-call transcripts), and the retrieval mechanism (hybrid keyword + semantic, with a 'phrase' mode). It also names the sibling it is not (ListFilings) and the follow-up tools (SearchDocument/ReadDocumentLines), so an agent can place it without opening a schema.

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?

Gives explicit when-to-use rules: omit ticker for market-wide vs. one ticker for single-company, and reserve excludeTickers/maxResultsPerCompany for market-wide discovery. It also names a concrete alternative (ListFilings for newest-first browsing without a text query), which is exactly the routing guidance an agent needs.

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

All Equibles tools Inspect

Try in Browser