Create a new ingredient unit in Mealie, defining its name, plural, abbreviation, aliases, and standard quantity for recipe measurements.
Create One — Recipes: Units. Create unit. [POST /api/units] Keywords: recipes_units_create_one, recipes units create one, create unit, add unit, new unit, make unit, write unit, unit, units, recipes units, create, add, new, make, write, post, mealie.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes |
Changes observed during successful MCP inspections.
v0.2.11Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description carries the full behavioral burden. It confirms a write via POST but says nothing about auth/permission requirements, whether creation fails on duplicate names, or what happens to defaulted fields. Only the endpoint class is disclosed.
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 operative text ('Create unit' + POST endpoint) is front-loaded, but it is then padded with a long keyword dump that repeats the name and title many times. The keyword block adds bulk without meaning.
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 create mutation with no annotations, no output schema, and a nested body at 0% description coverage, the definition is incomplete. It omits auth needs, duplicate/error behavior, and any body field guidance that the schema does not provide.
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 0% and there is one body parameter (a nested CreateIngredientUnit object with ~11 properties). At 0% coverage the description must compensate, but it adds no information about the body fields or their semantics, leaving the agent to infer everything from bare property titles.
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 clear verb+resource: 'Create unit' for 'Recipes: Units', and the POST /api/units endpoint disambiguates it from sibling unit tools like recipes_units_update_one. It does not explicitly differentiate itself from other create_* siblings (foods, tags, etc.), but the resource name is specific enough.
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 when-to-use, when-not-to-use, or alternative guidance is given. The keyword payload lists synonyms ('add unit', 'write unit') but never says when an agent should call this instead of recipes_units_merge_one or seed_units.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.