Compute the corporation tax position from figures (stateless, nothing stored): tax due, taxable profit, marginal relief, losses, CT600 box values.
| Name | Required | Description | Default |
|---|---|---|---|
| figures | Yes | The return figures, all in POUNDS. periodStart/periodEnd are ISO dates. |
Changes observed during successful MCP inspections.
Input schema / properties / figures / properties / taxAlreadyPaidAdded value: +{
+ "description": "Corporation tax the company has already paid HMRC for this period and has not had back (CT600 box 595), in pounds. 0 or absent if none. Not for a period over 12 months.",
+ "type": "number"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context beyond the annotations: the tool is stateless and persists nothing, and it names the outputs it produces. It does not, however, mention any input-validation behavior or error conditions.
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 front-loaded sentence: verb and resource first, then the stateless caveat, then a compact colon-list of outputs. Zero filler and nothing that needs to be read twice.
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?
With no output schema, the description usefully enumerates what the tool returns (tax due, taxable profit, marginal relief, losses, CT600 box values), and the stateless note answers the main caller concern. The deep nested input schema is fully documented on its own, so the remaining gap is only the absence of any routing guidance to sibling tools.
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% and the nested 'figures' object carries extensive per-field documentation (e.g. taxAlreadyPaid, fullExpensing, tradingStartDate), so the schema does the heavy lifting. The description adds nothing about individual parameters, which is the correct baseline of 3 when coverage is complete.
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?
States a specific verb (Compute) and resource (corporation tax position), and enumerates the concrete outputs (tax due, taxable profit, marginal relief, losses, CT600 box values). This clearly separates it from siblings like ct600_filing_guide and check_ct600_eligibility, which are advisory rather than computational.
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 parenthetical '(stateless, nothing stored)' implies it is safe to call freely and repeatedly, but the description never states when to reach for this tool versus siblings such as check_ct600_eligibility or ct600_filing_guide, nor any prerequisites. Usage is only implied.
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.