computeUniversal calculation entrypoint across all 30 TrueCalci engines. Dispatches execution to the specified engine with validated inputs, returning exact deterministic results.
| Name | Required | Description | Default |
|---|---|---|---|
| engine | Yes | The engine to run, by tool name (e.g. tds, fd, gst_composition). | |
| inputs | Yes | The engine's own inputs, exactly as its tool schema defines them. |
Changes observed during successful MCP inspections.
Input schema / properties / engine / descriptionPrevious value: -"Target engine name (e.g. 'tds', 'tcs', 'gst_regular', 'advance_tax', 'tax_in', 'contractor_parity', 'scorp_optimizer', 'cloud_egress_finops', 'compound_wealth')."New value: +"The engine to run, by tool name (e.g. tds, fd, gst_composition)."Input schema / properties / engine / exampleAdded value: +"tds"Input schema / properties / inputs / additionalPropertiesRemoved value: -trueInput schema / properties / inputs / descriptionPrevious value: -"Input parameters matching the target engine's schema."New value: +"The engine's own inputs, exactly as its tool schema defines them."Input schema / properties / inputs / exampleAdded value: +{
+ "amount": "50000.00",
+ "as_of_date": "2026-04-01",
+ "pan_available": true,
+ "pan_operative": true,
+ "payee_type": "individual_or_huf",
+ "payment_type": "contractor",
+ "resident": true
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly, idempotent, and non-destructive behavior. The description adds genuinely useful context beyond that: inputs are validated before dispatch, and results are 'exact deterministic' — a determinism claim not present in the annotations. No contradiction with annotations, and the additive behavioral traits are meaningful for an agent deciding whether repeated calls are safe and reliable.
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?
A single sentence of roughly 20 words with zero filler. The core concept (universal entrypoint, engine routing) is front-loaded, and the deterministic-results payoff is stated last. Every clause earns its place.
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 dispatcher that routes to 30 engines, the description handles complexity by deferring input details to each engine's schema, and the sibling list supplies valid engine names. It covers the return promise ('exact deterministic results') despite having no output schema. Minor gaps: no mention of error behavior for invalid engine names or unknown inputs, but this is acceptable for a routing tool whose contract lives in the target engines.
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 100% and both parameters (engine, inputs) are already well documented, including the nested structure and example for inputs. The description reinforces with 'validated inputs' and 'specified engine' but adds no format, syntax, or constraint detail beyond what the schema provides. At full coverage the baseline of 3 is appropriate.
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 states a clear purpose: a universal calculation entrypoint that dispatches to any of 30 TrueCalci engines and returns deterministic results. It implicitly distinguishes itself from the 31 sibling tools (tds, fd, gst_composition) by being the universal router rather than a specific engine. The name 'compute' is generic, but the title and description recover it with a specific verb (dispatches) and resource (engines).
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 implies usage — you route to a named engine rather than calling it directly — but it never explicitly says when to choose this universal entrypoint versus the specific engine tools, nor does it state any exclusion conditions. The 'route to any engine' title and the engine parameter hint at the decision, but there is no direct guidance on selection criteria.
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.