aether-developer

transcript_search

Read-onlyIdempotent

Search earnings-call transcripts and earnings press-release exhibits by speaker turn (CEO/CFO prepared remarks, analyst Q&A, press releases). Returns verbatim quotes as agent-ready payloads: speaker name/role, fiscal year + quarter, call date, source_type (asr_call = our own ASR of the real call vs press_release), sec.gov source URL and citation string. Use for guidance, management tone and forward-looking color that filings don't capture; pair with financial_search to back narrative with filed numbers. ALWAYS pass issuer (the ticker whose calls you mean) plus fiscal_year when you know it — a named call is scoped to that issuer's calls, fast and precise. A call with no issuer runs as scope=cross_company: slower, ranked by relevance only, and the response sets quality_caveat — check for that field. Use scope=cross_company deliberately, only for questions genuinely about many companies ("which management teams talked about tariff pass-through"). Narrow further with speaker_role, lookback_quarters or source_type. FETCH MODE: omit query entirely and pass issuer.ticker plus fiscal_year / quarter / date_from / date_to to get that call's segments back in call-date-desc then spoken order, with no ranking and in tens of milliseconds — the right tool when you already know WHICH call you want. For onset/"first mention" questions (when did a topic first come up), bound with date_from/date_to and set order='earliest' — a date pair, not a fiscal year, is the right tool there. Fetch mode pages: pass the response's next_offset as offset to read past limit. Returned windows overlap; counts of a term over returned text are not document counts. partial: true means retrieval degraded; an empty result is then not proof of absence. A cross_company call that times out returns a clean 503 telling you to name an issuer.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No
`order`	No	Sort order. 'earliest'/'latest' sort matched hits chronologically (use 'earliest' for onset/first-mention queries); 'relevance' sorts by rank score.	relevance
`query`	No	Natural language query. OMIT IT for fetch mode: with no query nothing is embedded or scored and the matching segments come back newest call first, then in the order they were spoken. Fetch mode requires a ticker.
`scope`	No	issuer (default): results limited to the issuer's own calls. cross_company: search every issuer's calls — slower, relevance-ranked only, and always carries `quality_caveat`. Setting it drops the ticker filter, so a caveated answer is never secretly a scoped one.	issuer
`issuer`	No	The company whose calls you mean. Pass `ticker` (e.g. "NVDA"); this corpus is keyed on ticker, so that is the field that scopes it. Strongly recommended on every call.
`offset`	No	Fetch mode only: paging cursor. Omit (or 0) for the first page, then pass the previous response's `next_offset` until it is absent.
`ticker`	No	Optional ticker filter (e.g. NVDA). Legacy alias of `issuer.ticker`.
`date_to`	No	Point-in-time upper bound on call date, inclusive ISO YYYY-MM-DD
`profile`	No		hybrid
`quarter`	No	Fiscal quarter(s) — "Q2" or ["Q1","Q2"]. Exact, case-insensitive. With issuer.ticker and fiscal_year this names one call, which is the natural fetch-mode request.
`date_from`	No	Point-in-time lower bound on call date, inclusive ISO YYYY-MM-DD
`fiscal_year`	No	Fiscal year(s) the question concerns — the ISSUER'S OWN fiscal year, as printed on its cover page, matched exactly against each segment's fiscal-year label. Offset-fiscal-year issuers work as stated: NVDA fiscal_year 2027 returns the calls held during calendar 2026, AAPL 2025 the Q1-Q4 FY2025 calls. If the requested year matches nothing the search retries once at ±1 and says so in `quality_caveat`. Independent of date_from/date_to, which bound the CALL DATE and still apply on top.
`source_type`	No	Provenance filter: asr_call = our ASR of the real call (Q&A); furnished_transcript = issuer transcript exhibit; press_release = 8-K press exhibit.
`speaker_role`	No	Optional speaker role filter: CEO / CFO / Analyst / Operator
`lookback_quarters`	No	Keep calls within last N quarters (default: no filter)

Output Schema

TableJSON Schema

Name	Required	Description
`mode`	Yes	"search" = ranked by relevance. "fetch" = no ranking; segments listed newest call first then in spoken order, and `confidence` is 0 on every result because there is no relevance signal.
`query`	Yes
`scope`	No	Effective scope after issuer resolution.
`total`	Yes
`source`	Yes
`partial`	No	True when retrieval degraded (lexical-only because the semantic arm was unavailable). Not proof of absence.
`results`	Yes
`latency_ms`	Yes
`next_offset`	No	Fetch mode: more segments exist; pass this as `offset` for the next page. Absent on the last page.
`ticker_filter`	No
`partial_reason`	No
`quality_caveat`	No	Present when the result is not issuer-precise. Read it before trusting cross-company results.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 10, 2026

addedInput schema / properties / offset

Added value: +{
+  "description": "Fetch mode only: paging cursor. Omit (or 0) for the first page, then pass the previous response's `next_offset` until it is absent.",
+  "minimum": 0,
+  "type": "integer"
+}

addedOutput schema / properties / next_offset

Added value: +{
+  "description": "Fetch mode: more segments exist; pass this as `offset` for the next page. Absent on the last page.",
+  "type": "integer"
+}

addedOutput schema / properties / partial

Added value: +{
+  "description": "True when retrieval degraded (lexical-only because the semantic arm was unavailable). Not proof of absence.",
+  "type": "boolean"
+}

addedOutput schema / properties / partial_reason
```
Added value: +{
+  "type": "string"
+}
```

First observedSep 11, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses a lot of runtime behavior: cross_company sets quality_caveat, partial:true means degraded retrieval so empty is not proof of absence, fetch mode returns unordered segments in milliseconds, windows overlap so term counts are not document counts, and a cross-company timeout yields a clean 503. This is exactly the kind of context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

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

The critical guidance (purpose, issuer requirement, cross_company caveat) is front-loaded, and nearly every sentence carries operational information. It is nonetheless one dense block that could be broken into labeled sections; the length is justified by the tool's complexity but not ideal for scanning.

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 15-parameter tool with nested objects, enums, and an output schema, the description is complete: mode selection, scoping, paging, degradation signals, and timeout behavior are all covered. Return-value structure is largely delegated to the output schema, as appropriate, with only the fields needed for follow-up actions called out.

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 coverage is 87%, so the baseline is 3, but the description adds cross-parameter meaning the schema doesn't: that issuer.ticker is the scoping field, that fetch mode requires a ticker, that date_from/date_to are independent of and applied on top of fiscal_year, and that offset takes the prior response's next_offset. Much of the fetch-mode text duplicates the schema's query and offset descriptions, which keeps this just short of a 5.

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 (search earnings-call transcripts and press-release exhibits) and immediately scopes it by speaker turn and provenance. It also names the sibling it complements (financial_search) and what it covers that filings don't, so an agent can distinguish 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: always pass issuer+fiscal_year, use scope=cross_company only for genuinely multi-company questions, use fetch mode when the exact call is known, and use a date pair rather than a fiscal year for onset/first-mention questions. It also names the alternative (financial_search) and the pairing rationale.

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

All aether-developer tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.