OpenInvest

record_balance_observation

DestructiveIdempotent

Record client-supplied balance observations—value, native quantity, or per-unit cost—with original as-of time and source provenance for audit-only tracking.

Instructions

Record independent value, native quantity or per-native-unit average cost observations.

No value-to-quantity conversion, cash movement, inferred fill or historical return approval. Historical/mismatched evidence stays audit-only. Invoke only for facts the client actually supplied, with its original as-of time.

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": {
      "reference_symbol": "<reference_symbol>",
      "as_of": "<as_of>",
      "source_text": "<source_text>",
      "source_locator": "<source_locator>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "record_balance_observation"
  }
}

Input Schema

Name	Required	Description
`as_of`	Yes	Timezone-aware time of the reported balance, separate from today's server receipt time.
`source_text`	Yes	Original client statement or description of the source. Never reconstruct it from an Agent's old summary.
`cost_currency`	No
`quantity_unit`	No
`reported_cost`	No
`reported_value`	No
`source_locator`	Yes	Source locator text or JSON object as text. This records client provenance; it does not claim broker verification.
`value_currency`	No
`idempotency_key`	Yes	Reuse the same key and unchanged facts when retrying.
`reference_symbol`	Yes	Existing tracked position. A quote proxy is not automatically the native instrument.
`native_instrument`	No
`reported_quantity`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.68.10Nov 9, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare the write/destructive/idempotent profile, so the bar is lower, yet the description adds real behavior: historical or mismatched evidence is retained audit-only rather than producing adjusted returns, and no conversion or cash-movement side effects occur. It still doesn't say what happens on a rejected or conflicting submission or what the write produces.

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?

Three tight sentences, front-loaded with what is recorded, followed by exclusions and the invocation condition. The second sentence is a compressed list that takes a moment to parse but carries no filler.

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 12-parameter destructive write with an output schema already covering return values, the description supplies the provenance discipline, the no-conversion invariant, and the audit-only fallback that an agent could not derive from structured fields. The remaining gap is failure/conflict behavior and the relationship between reference_symbol and native_instrument.

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

Parameters3/5

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

Schema coverage is only 42% with 12 parameters, so the description is partly responsible for compensating, and it does explain that reported_cost is a per-native-unit average and that value and quantity must not be converted between. It says nothing about the currency pair fields, native_instrument, source_locator, or the reference_symbol relationship, leaving several bare parameters undocumented in both places.

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 gives a specific verb ('Record') and a precisely scoped resource (independent value, native quantity, or per-native-unit average cost observations), which is materially more specific than the tool name alone. It does not, however, explicitly differentiate itself from nearby siblings such as record_existing_position or record_execution, leaving the agent to infer the boundary.

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

Usage Guidelines4/5

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

It states a clear inclusion rule ('Invoke only for facts the client actually supplied, with its original as-of time') and four explicit exclusions (no value-to-quantity conversion, no cash movement, no inferred fill, no historical return approval). What it lacks is a named alternative for the excluded cases, so the agent knows when not to use it but not where to go instead.

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