Capital-gains / income tax estimate for a year: gains, losses, exemption (including any carried-forward amount), taxable base and estimated tax.
| Name | Required | Description | Default |
|---|---|---|---|
| year | No | Defaults to the current year | |
| account | No | One portfolio; absent sums every configured one |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It describes the tool as providing an 'estimate' and mentions carried-forward amounts, but does not explicitly declare it as read-only, disclose authentication requirements, or describe side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that efficiently lists key output components. While dense, it contains no redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description compensates by listing report contents. It covers the main purpose and parameter usage (year default, account summing). Missing is a mention of data format (e.g., object with fields).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage with defaults. The description adds value by enumerating what the report includes (gains, losses, exemption, etc.), giving the agent context beyond parameter names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool provides a capital-gains/income tax estimate for a year, listing specific output components (gains, losses, exemption, taxable base, estimated tax). It distinguishes itself from siblings like get_dashboard or get_net_worth_history.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance is given. The description implies it is for tax estimates, but does not compare to alternatives like get_dashboard or list_transactions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct domain operation: dashboard views, history, pricing, projections, reference data, tax reports, connections, transactions, trade logging, balance adjustments, and syncing. There is no overlap between read-only queries and mutation commands, so an agent should be able to select the right tool for a specific task without confusion.
All tools follow a consistent verb_noun pattern: get_dashboard, get_net_worth_history, get_prices, get_projection_config, get_reference_data, get_tax_report, list_connections, list_transactions, log_trade, record_balance_adjustment, refresh_prices, sync_connections. The verbs (get, list, log, record, refresh, sync) are clear and align with the noun they operate on.
Twelve tools is well-scoped for a personal finance/ledger server. Each tool covers a necessary aspect of the domain (viewing, reporting, data entry, sync), and none feel redundant or excessive. This fits the typical range for a coherent service.
The surface covers core read operations (dashboard, history, prices, reference data, tax, transactions), mutation operations (log_trade, record_balance_adjustment), and maintenance operations (refresh_prices, sync_connections). Missing could be an update/delete for transactions or connections, but the provided tools cover the primary lifecycle of a financial ledger without dead ends.
