Deep Values

Point-in-time fundamentals: what was filed as of a date, before restatement

as_filed

Read-only

Call this when the question is about what was known on a past date (a backtest, an audit, "what did the 10-K say at the time"), not about the current restated figures. Returns, for each fiscal period filed on or before date, the value as it stood on that date (the original filing, or a later filing for the same period if it came before date), the filing date, the XBRL tag, a sec.gov link, and restated_after_date when a later filing changed it. Values are as printed, not split-adjusted. Inputs: ticker (path), date (YYYY-MM-DD, required), metrics (comma-separated snake_case names, default revenues,net_income,eps_diluted,operating_cash_flow,free_cash_flow,stockholders_equity,total_debt,shares_outstanding), period (annual|quarterly), limit (periods, default 4). Example: GET /as-filed/AAPL?date=2020-02-01&metrics=revenues,net_income. If the company had filed none of it by date, the answer has no periods, the flag nothing_filed_by_date and earliest_filed (the first filing date on record). A 503 as-filed-unavailable means there is no as-filed history for the company to answer from; it is not charged, and GET /fundamentals has the current figures. 0.01 credits. (GET https://app.deepvalues.ai/api/v1/as-filed/{ticker} — 0.01 credits per call; works with no credentials up to 5 call(s)/day per address)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ticker": "<ticker>",
      "date": "<date>"
    },
    "name": "as_filed"
  }
}

Input Schema

Name	Required	Description	Default
`date`	Yes	The day to look back from (YYYY-MM-DD, 2009-01-01 or later, not in the future).
`limit`	No	How many of the most recent periods filed by `date` to return.
`period`	No		annual
`ticker`	Yes
`metrics`	No	Comma-separated metric names (snake_case), at most 20.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 4, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the readOnly/openWorld annotations, it discloses non-obvious traits: values are as originally printed and not split-adjusted, each row can carry a `restated_after_date` flag, an empty result yields `nothing_filed_by_date` plus `earliest_filed`, and a 503 `as-filed-unavailable` is not charged. The credit cost (0.01) and the credential-free 5 calls/day allowance are also stated. Nothing here contradicts readOnlyHint=true.

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?

It is front-loaded with the usage condition, then behavior, then inputs, then edge cases -- a sensible order. The single dense paragraph is long and mixes usage guidance with pricing/access boilerplate at the tail, which slightly dilutes scanability, but nearly every sentence carries information an agent needs.

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?

With no output schema, the description carries the return-value burden itself and does so: it enumerates returned fields (value, filing date, XBRL tag, sec.gov link, restated_after_date) and describes the empty-result shape and the 503 case. For a 5-parameter read tool this leaves nothing material uncovered.

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 60%, and the description compensates by supplying the default `metrics` list (revenues, net_income, eps_diluted, operating_cash_flow, free_cash_flow, stockholders_equity, total_debt, shares_outstanding), the YYYY-MM-DD date format, limit as a count of periods, and annual|quarterly. It stops short of enumerating every valid snake_case metric name, so an agent still has to infer whether an arbitrary metric is accepted.

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?

The description states a specific verb and resource -- returns fundamentals as they were filed on or before a date, before restatement -- and explicitly contrasts itself with the sibling tool that returns current figures (GET /fundamentals). The title and opening sentence let an agent separate this from `fundamentals` without opening either 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?

It gives a concrete trigger ('when the question is about what was known on a past date'), names use cases (backtest, audit, 'what did the 10-K say at the time'), and explicitly excludes the current-figures case while naming the alternative (`/fundamentals`). Both the when and the when-not are stated.

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

All Deep Values 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.

Resources

Need Help?