Look up the current-law dollar amounts behind a question ('standard deduction', 'CTC phase-out threshold', 'tips deduction cap') with their statutory citations and validity windows. Use this to fact-check ANY tax number before stating it — your training data likely predates the OBBBA.
| Name | Required | Description | Default |
|---|---|---|---|
| asOf | No | ||
| query | Yes | plain-English search, e.g. 'standard deduction' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description discloses that it returns current-law amounts, statutory citations, and validity windows. It also warns about outdated training data, which is helpful. It does not mention error handling or read-only nature, but the intended behavior is clear.
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?
Two sentences: the first clearly defines purpose and output, the second provides usage guidance. Every sentence is valuable and there is no redundancy.
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?
For a simple lookup tool with 2 parameters and no output schema, the description covers what it returns (citations, windows) and when to use it. It lacks details on what happens for missing queries or the exact format of citations, but it is largely sufficient.
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?
Schema coverage is 50% (query has description, asOf only has pattern). The description adds value by explaining query as 'plain-English search' with an example. However, the asOf parameter lacks semantic explanation beyond the date pattern, leaving ambiguity.
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 looks up current-law dollar amounts behind specific tax questions, provides examples like 'standard deduction' and 'CTC phase-out threshold', and explicitly says it returns statutory citations and validity windows. This distinguishes it from sibling tools like verify_fact or search_tax_rules.
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?
The description explicitly advises to 'fact-check ANY tax number before stating it' because training data may be outdated. It implies the primary use case but does not explicitly mention when not to use it or alternatives.
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 has a clearly distinct purpose: calculate_tax handles individuals, calculate_business_tax handles entities, calculate_fiduciary_tax handles estates/trusts, compute_return produces the complete federal return, compute_state_return handles state returns, and the remaining tools cover specific lookups (parameters, rules, facts, dependencies, cliffs, tipped occupations) or verification. Even with overlapping domains (explain_rule, lookup_tax_parameter, search_tax_rules, verify_fact, verify_tax_claim), their roles are sharply delineated.
Tool names follow a clear pattern: compute_return, compute_state_return, calculate_tax, calculate_business_tax, calculate_fiduciary_tax, determine_dependent, explain_rule, find_tax_cliffs, is_tipped_occupation, list_input_facts, lookup_tax_parameter, search_tax_rules, verify_fact, verify_tax_claim. Most use verb_noun (calculate_tax, lookup_tax_parameter, search_tax_rules, verify_fact). Minor deviations: compare_filing_statuses and compute_return use adjective/noun phrases rather than verb_noun, but they're still readable and follow the 'compute/calculate' theme.
15 tools is well-scoped for a comprehensive tax computation server. Each tool covers a distinct aspect of tax law (federal individual, business, fiduciary, state returns, dependency, rule lookup, parameter lookup, validation, cliff detection, fact verification, search). No tool feels redundant, and the count supports the ambitious scope without bloating.
The tool surface covers the full tax workflow: input discovery (list_input_facts), computation (calculate_tax, calculate_business_tax, calculate_fiduciary_tax, compute_return, compute_state_return), dependency determination (determine_dependent), rule/parameter lookup (explain_rule, lookup_tax_parameter, search_tax_rules), verification (verify_fact, verify_tax_claim), and specialized analysis (find_tax_cliffs, is_tipped_occupation, compare_filing_statuses). There's no obvious gap; the only potential missing feature is payroll tax computation, but that's outside the stated domain of income tax.
