savi-tools

Tax deductions

get_tax_deductions

Read-only

Deductible costs mapped onto the lines of the tax return the business actually files (Schedule C, 1120, 1120-S, 1065, or 990), with entity-aware treatment (meals at 50%, etc.). Answers "what are my deductions this year and where do they land on my return?"

Input Schema

TableJSON Schema

Name	Required	Description	Default
`year`	No	Calendar year. Omit to use the current fiscal year.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`form`	Yes
`basis`	No
`lines`	Yes
`method`	Yes
`formLabel`	Yes
`periodEnd`	Yes
`periodStart`	Yes
`totalDeductions`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 20, 2026

addedOutput schema / properties / basis

Added value: +{
+  "properties": {
+    "accountingMethod": {
+      "type": "string"
+    },
+    "definitions": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "timezone": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "timezone",
+    "definitions"
+  ],
+  "type": "object"
+}

Changed1 schema field changedJul 16, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "form": {
+      "type": "string"
+    },
+    "formLabel": {
+      "type": "string"
+    },
+    "lines": {
+      "items": {
+        "properties": {
+          "amount": {
+            "type": "number"
+          },
+          "line": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "line",
+          "amount"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "method": {
+      "type": "string"
+    },
+    "periodEnd": {
+      "type": "string"
+    },
+    "periodStart": {
+      "type": "string"
+    },
+    "totalDeductions": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "form",
+    "formLabel",
+    "method",
+    "periodStart",
+    "periodEnd",
+    "totalDeductions",
+    "lines"
+  ],
+  "type": "object"
+}

First observedJul 15, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already mark readOnlyHint=true and destructiveHint=false. The description adds detail by disclosing entity-aware treatment (e.g., meals at 50%) and that it handles multiple entity types. It could mention how year is determined when omitted, which is covered by schema.

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?

Two sentences, front-loaded with the core purpose and entity-specific details, then a clarifying question. No fluff.

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 read-only filter/report tool with a single optional parameter and output schema present, the description adequately covers usage. It could go into more depth about tax return line specifics but is complete for its scope.

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 100%; the single 'year' parameter is documented. The description implies the year's role but doesn't add semantics beyond the schema. Baseline 3 is appropriate.

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?

The description uses a specific verb ('get'), resource ('tax deductions'), and business context (tax return lines for Schedule C, 1120, etc.). It clearly differentiates from siblings by focusing on deduction-to-tax-line mapping rather than generic summaries.

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?

The description explains what the tool does and answers a specific question, implying when to use it (when deductions need to be mapped to tax return lines). It does not explicitly name alternatives, but the entity-aware treatment and reference to specific forms provide enough context for selection.

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

All savi-tools tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?