Validate or create a tax return by specifying taxpayer, tax year, and return type; use commit mode to finalize.
Create or validate creation of a tax return. Mutations default to validate-only.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | validate (default) or commit | |
| tax_year | Yes | ||
| return_type | Yes | ||
| taxpayer_ref | Yes | Opaque taxpayer reference. Do not pass a SIN directly through the MCP tool. |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden of behavioral disclosure. It usefully reveals that mutations default to validate-only, meaning the tool does not commit changes unless explicitly set to commit mode. The SIN warning in the schema also adds important safety context, though the description itself does not discuss side effects or commit-mode consequences.
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 only two sentences and front-loads the core purpose. The phrase 'Create or validate creation' is slightly awkward and redundant, but the overall text is efficient and every sentence contributes meaningful information.
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 covers the tool's main intent and its default validate-only behavior, which is essential for safe invocation. However, with no output schema and no annotations, it does not explain what validation returns, what commit does exactly, or what errors might occur, leaving moderate gaps for an agent.
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 tool description adds no parameter-level meaning. Schema description coverage is only 50%, with tax_year and return_type left undocumented; the description does not compensate for those gaps. It relies entirely on the schema's mode and taxpayer_ref descriptions, which are insufficient for full agent comprehension.
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 states a specific action ('Create or validate creation') and a resource ('tax return'), and the 'validate-only' default clarifies the tool's dual behavior. It is distinguishable from sibling list/read tools like list_returns or set_field, though it doesn't explicitly name a sibling.
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 description implies this tool is used to create or validate a tax return, but it does not explicitly say when to use it versus alternatives or what conditions favor validate vs. commit mode. The 'Mutations default to validate-only' sentence gives contextual guidance, but no exclusions or alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.