get_dilution_instruments

shallow

ai.signal8/mcp ยท Verify this server

Get ONE instrument family's rows (10 credits) with per-field SEC citations โ€” each figure carries the accession number, filing date and the verbatim quoted sentence it was read from, so every number can be traced to a filing. Families: warrants, convertibles, preferred, shelfs, atms, elocs, s1_offerings, equity_plans, exchangeables, recent_offerings. One family per call โ€” request the families you actually need rather than sweeping all ten. ๐Ÿ”ด ROW-LEVEL WITHHOLDING: `withheldRows` / `withheldRowCount` mean specific rows could NOT be verified and were blanked, so every family total in the response is a LOWER BOUND, not a complete figure. Say so โ€” presenting a holed total as complete understates a named issuer's dilution. An empty rows array on a covered company is a measured "none found in the filings read"; an unavailable response is not. ALWAYS RETURNS 200 โ€” read `available` and `reason`, never the HTTP status. Coverage is partial: `not_covered` means THIS COMPANY HAS NOT BEEN ANALYSED YET, which is different from it having no dilution and different from an outage (an outage is a 5xx). Never report a company as having no dilution on the strength of an unavailable response. NULL, absent or withheld means NOT MEASURED โ€” it NEVER means "no dilution", "no warrants", "no shelf" or zero. A numeric 0 is a MEASURED zero and defeats a null check, so decide from the accompanying availability/withheld/reason field, never from the value itself. If a figure is absent, say it was not measured; do not describe the company as having none of that instrument. Figures are as of `meta.asOfDate`, from filings read through `meta.filingsThrough` โ€” a stale as-of date means the answer predates anything filed since, not that nothing has happened. Share counts are rebased onto a single split basis; a row that cannot be rebased is omitted and counted rather than published on a mixed basis. Included in Signal8 Pro โ€” without it the call returns 403 with code FEATURE_NOT_AVAILABLE and `requiredTier: "pro"`. That is a subscription-tier upgrade, not an add-on purchase; there is no separate add-on to buy.

100.0/100

1 trials ยท measured 26 days ago

get_dilution_instruments scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against ai.signal8/mcp, measured 23 Sept 2026 under methodology v0.2.0. Every measured component scored 100.

Component breakdown

ComponentWeightValue
Reliability35%not applicable
Schema integrity25%100.0
Failure behaviour15%not applicable
Latency15%not applicable
Concurrency10%not applicable

Tool details

Transport
remote + stdio
Credential class
gated
Input schema
not declared
Output schema
not declared
Side-effect classification
unclassified

Score history

DayScoreTierMethodology
2026-09-23100.0shallowv0.2.0

Probe evidence

ProbeOutcomes
schema_integritypass: 1

Raw request/response logs are not archived yet โ€” the outcome counts above are drawn directly from every recorded trial.

Embed this score

Available for every tool, scored or not โ€” not a verification perk. Always links back to this page.

Vouch score: get_dilution_instruments
[![Vouch score](https://vouch.tools/api/tools/a74dac18-1571-417f-a0f8-936b4575cb33/badge.svg)](https://vouch.tools/tools/a74dac18-1571-417f-a0f8-936b4575cb33)
get_dilution_instruments โ€” Vouch