HelloBooks AI Agents

analyze_journal_variance

Compare two periods of journal-entry data (QBO or Xero — source auto-detected from headers) and flag accounts whose movement deviates materially between periods. Aggregates lines per account into a net total for each period, then surfaces accounts where the period-over-period change crosses a materiality threshold (≥5% relative AND ≥$100 absolute; severity high at ≥50%, medium at ≥20%, low at ≥5%). Inputs are two CSV exports — periodACsv (earlier period) and periodBCsv (later period). Optional periodALabel / periodBLabel for human-readable flag messages (e.g. "Q1 FY2024" vs "Q2 FY2024"). Max 5,000 rows per period; max 5 MB each. Use this when a user pastes two periods and asks "what changed?", "show me variances", "what jumped period-over-period". Returns a flag list ordered by largest delta, a roll-up, and a shareable URL. Both periods must be the same source — mixing QBO + Xero in one call returns an error.

Input Schema

TableJSON Schema

Name	Required	Description
`periodACsv`	Yes	Raw CSV text of the EARLIER period's journal-entry export (QBO Journal Entries or Xero Manual Journals). Source is auto-detected from the headers.
`periodBCsv`	Yes	Raw CSV text of the LATER period's journal-entry export. Source is auto-detected from the headers (must match periodACsv).
`periodALabel`	No	Optional human label for the earlier period — e.g. "Q1 FY2024". Used in flag messages.
`periodBLabel`	No	Optional human label for the later period — e.g. "Q2 FY2024".

TDQS

A4.4/5.0

Behavior4/5

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

Describes aggregation, threshold logic (≥5% relative and ≥$100 absolute with severity levels), output format (flag list, roll-up, shareable URL), and error condition (mixing sources). Without annotations, it covers key behaviors well, though no mention of read-only/destructive nature.

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?

Front-loaded with purpose, then detailed constraints and logic. Every sentence contributes value; slight redundancy in source-matching requirement but overall efficient.

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?

Given complexity (two CSVs, auto-detection, threshold logic, no output schema), description covers input requirements, processing, output format, and error conditions thoroughly. No gaps evident.

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 100%, but description adds crucial semantics: clarifies earlier vs later period, auto-detection, max sizes, optional labels for human readability. Adds value beyond schema.

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?

Clearly states the tool compares two periods of journal-entry data and flags accounts with material variance. Differentiates from sibling tools like anomaly detection or cleanup tools by focusing on period-over-period variance for both QBO and Xero.

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?

Provides explicit use cases (e.g., 'what changed?', 'show me variances') and constraints (max rows/size, source matching). Lacks explicit 'do not use when' statements but gives strong positive guidance.

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

All HelloBooks AI Agents tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose, with detailed descriptions that specify the exact input and use case. Even similar tools like QBO vs Xero journal analyzers are differentiated by source system and specific checks, leaving no ambiguity.

Naming Consistency4/5

The majority of tools follow a verb_noun snake_case pattern (e.g., analyze_balance_sheet, list_features). A few exceptions like how_munimji_helps and feature_search deviate slightly, but overall the convention is consistent and readable.

Tool Count4/5

With 26 tools covering financial analysis, compliance, migration, and product info, the count is on the higher side but justified by the breadth of the accounting domain. Each tool serves a specific need without redundancy.

Completeness4/5

The tool set covers all major financial statement checks (balance sheet, P&L, trial balance, journal entries), compliance, migration, and product details. A notable gap is the lack of cash flow analysis, but the set is otherwise comprehensive for its scope.

Resources

Need Help?