calculateRun the Settlement agreement estimator calculator: Statutory redundancy baseline; Typical ex-gratia, lower end; Typical ex-gratia, upper end; Typical package, lower end. Missing inputs fall back to their documented defaults.
| Name | Required | Description | Default |
|---|---|---|---|
| years | No | Complete years of service | |
| salary | No | Gross annual salary | |
| ageBand | No | Your age band | b41plus |
| circumstances | No | What the exit looks like | redundancy |
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 carries the burden of behavior; it adds useful context by listing what the calculator returns and noting that missing inputs fall back to defaults. It doesn't explicitly state that this is a read-only, side-effect-free estimation (unlike submit_enquiry), but 'calculator' and the output-only framing make the lack of side effects reasonably inferable.
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 short sentences, with the core action front-loaded and the output categories compactly listed. The default-fallback note earns its place by protecting against assumption errors, and there is no redundant wording.
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 calculator with zero required parameters and fully documented inputs, the description covers what is calculated and the fallback behavior. It doesn't specify the return format or numeric rounding because there is no output schema, but the listed output categories give enough context for an agent to interpret the result.
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 schema already documents all four parameters at 100% coverage, so the description is not required to re-explain them. It adds only the general statement that missing inputs use defaults, which is a useful reminder but not parameter-specific meaning.
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 names the exact resource ('Settlement agreement estimator calculator') and the action ('Run'), and enumerates the specific outputs it produces, so an agent can tell it's the calculator rather than the enquiry/submission siblings. It doesn't explicitly point to a distinguishing sibling, but the verb and output list make the purpose unambiguous.
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?
There is no statement about when to choose this calculator over calculator_describe or the enquiry/submission tools, and no exclusion or alternative behavior. The only contextual hint is the output list, which implies calculation use but leaves the selection logic to inference.
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 clear role: calculate runs the estimator, the describe/fields tools provide reference information, and submit_enquiry handles the enquiry flow. There is minor potential confusion between calculator_describe and enquiry_describe since both are describe-style tools, but their targets are clearly different.
Tool names mix patterns: 'calculate' and 'submit_enquiry' are verb-first, while 'calculator_describe' and 'enquiry_describe' are noun-first, and 'enquiry_fields' is noun-only. The inconsistent ordering makes the set feel less predictable than it could be.
Five tools is a well-scoped size for a site centered on a settlement calculator and an enquiry submission flow. Each tool covers a distinct need without bloat or unnecessary granularity.
The surface covers the full expected lifecycle: running the calculator, understanding its inputs/outputs, understanding what the enquiry does, retrieving the enquiry fields, and submitting the enquiry with confirmation handling. No obvious dead ends or missing operations for the stated domain.