Set or validate a tax field in Canadian tax software through a vendor-neutral concept layer; defaults to validate-only.
Set or validate a tax field using a vendor-neutral concept. Mutations default to validate-only.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | validate (default) or commit | |
| value | Yes | ||
| concept | Yes | ||
| tax_year | Yes | ||
| return_id | Yes | ||
| evidence_page | No | ||
| evidence_checksum | No | ||
| evidence_source_id | No | ||
| evidence_source_type | No |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It usefully discloses that mutations default to validate-only, an important safety-relevant behavior. However, it omits other behavioral details such as what a committed mutation does, whether the action is reversible, required permissions, or what the response looks like.
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 two short sentences with no filler, and the primary action is front-loaded. It is efficiently structured, although it could use the saved space to add a bit more parameter or behavior guidance.
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 9 parameters, 4 required, no output schema, and no annotations, the description is not complete enough for reliable invocation. It does not explain how evidence parameters relate to validation/commit, what validate-only mode returns, or what commit actually does, leaving substantial 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?
Schema description coverage is only 11%, so the description must compensate for undocumented parameters. It adds meaning for 'concept' (vendor-neutral) and indirectly for 'mode' (mutations default to validate-only), but it leaves the required return_id, tax_year, and value, as well as all evidence_* parameters, without semantic explanation.
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 a specific verb ('Set or validate'), a clear resource ('a tax field'), and the key qualifier ('using a vendor-neutral concept'). This distinguishes set_field from the read-oriented sibling get_field and the concept-listing sibling list_concepts.
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 that the tool is used to set or validate a field, and notes that mutations default to validate-only, which gives context for the mode parameter. However, it does not explicitly say when to choose 'validate' versus 'commit', nor does it mention alternatives such as get_field for reading or list_concepts for finding valid concepts.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.