calculateRun the UAE corporate tax calculator calculator: Taxable income brought into charge; Taxed at 0%; Taxed at 9%; Corporate tax for the period. Missing inputs fall back to their documented defaults.
| Name | Required | Description | Default |
|---|---|---|---|
| sbr | No | Electing Small Business Relief? | 0 |
| income | No | Taxable income for the tax period | |
| status | No | Which describes the business? | standard |
| revenue | No | Revenue for the tax period |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral disclosure. It usefully discloses that missing inputs fall back to documented defaults and that output includes four labeled figures. It does not explicitly state that the tool is side-effect-free or describe calculation assumptions, but the calculator nature makes this less critical.
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 dense sentence with the action front-loaded and the fallback behavior included. The redundant 'calculator calculator' and the semicolon-separated output list slightly reduce clarity, but it is still compact.
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?
The description lists the return values and fallback behavior, which is necessary because there is no output schema or annotations. It remains somewhat incomplete: it does not explain output format, units, or how the input parameters map to the tax rates, and no usage example is provided.
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 covers 100% of the parameters, so the baseline is 3. The description adds nothing about how sbr, income, status, or revenue influence the calculation beyond referencing their documented defaults.
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 identifies a clear action ('Run') and resource (UAE corporate tax calculator), and it enumerates the computed outputs. It is distinguishable from sibling calculator_describe and enquiry tools even without naming them, though the duplicate 'calculator calculator' is a minor wording defect.
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 use case is implied: use this tool when you need to run the UAE corporate tax calculation. However, there is no explicit guidance about when not to use it or how it compares to calculator_describe, enquiry_describe, or submit_enquiry.
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 role: calculate runs the tax computation, calculator_describe documents the calculator, enquiry_describe explains the enquiry process, enquiry_fields defines the input schema, and submit_enquiry handles submission. There is no meaningful overlap between any two tools.
The naming is readable and grouped by domain, but conventions are mixed: calculate is a plain verb, calculator_describe and enquiry_describe use noun_verb order, enquiry_fields is noun_noun, and submit_enquiry is verb_noun. A consistent verb_noun or describe_* pattern would make the set more predictable.
Five tools is an appropriate size for a focused calculator-plus-enquiry server. Each tool covers a distinct piece of the workflow and none feel redundant or decorative.
The calculator side is complete with calculate and calculator_describe, and the enquiry side has field introspection, process disclosure, and two-step submission. The only minor gap is the lack of any post-submission status or history tool, but the flow is designed around email confirmation so this is not a critical omission.