calculateRun the PAYE deadline calculator, 2026/27 calculator: Pay HMRC by; Send your Full Payment Submission (FPS); Tax month this payday falls in; Employer Payment Summary (EPS) deadline. Missing inputs fall back to their documented defaults.
| Name | Required | Description | Default |
|---|---|---|---|
| payDay | No | Day of the month you pay them | |
| payMonth | No | Month you pay your staff | aug26 |
| payMethod | No | How you pay HMRC | 0 |
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?
There are no annotations, so the description must carry the transparency burden. It does disclose one useful behavior: missing inputs fall back to documented defaults, and it lists the values the calculator produces. However, it does not explicitly state that the operation is read-only, nor describe what happens on invalid inputs, so some behavioral context is missing.
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 relatively short and front-loads the command, but it contains a redundancy ('calculator, 2026/27 calculator') and uses a choppy semicolon list. The content is useful, but the phrasing is not polished enough for a higher score.
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 three optional parameters, the description covers the main purpose and default behavior. But since there is no output schema, it only names the output concepts without describing the response format or edge-case behavior, leaving some ambiguity for an agent invoking the tool.
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 description coverage is 100%, so the parameters are already documented in the input schema (payDay, payMonth, payMethod). The description adds only a general default-fallback note and no parameter-specific insight, which matches the baseline of 3.
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 uses a specific action ('Run the PAYE deadline calculator') and names the concrete outputs: HMRC payment date, FPS submission, tax month, and EPS deadline. This clearly states what the tool does, though it never explicitly distinguishes it from sibling tools like calculator_describe.
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?
No guidance is given for when to choose this tool over the sibling tools; calculator_describe and the enquiry tools are never mentioned. The only usage-adjacent note is about fallback defaults, which does not help an agent decide between 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 role: one runs the calculator, one describes the calculator, one explains the enquiry flow, one provides enquiry fields, and one submits the enquiry. Even the two 'describe' tools are cleanly separated by subject matter and explicit descriptions.
The names mix verb-only ('calculate'), noun-first with verb suffix ('calculator_describe', 'enquiry_describe'), and verb-noun ('submit_enquiry'), with 'enquiry_fields' following a noun-noun pattern. The style is readable and consistently lowercase/underscore, but the naming conventions are not uniform.
Five tools is well-scoped for a server that provides a single deadline calculator plus a guided enquiry submission flow. Each tool earns its place, and there is no bloat or sense of missing infrastructure.
The calculator has both a run tool and a describe tool to expose assumptions, and the enquiry flow has describe, fields, and a two-step submit tool with confirmation handling. The surface covers the full lifecycle for the server's apparent purpose.