forget_tasteDelete one entry from the org's learned taste by its id (from get_profile taste or remember_taste). This is how the user's "undo" works.
| Name | Required | Description | Default |
|---|---|---|---|
| tasteId | Yes | tasteId (path). | |
| commandId | No | Retry identity. A call repeated with the same commandId returns the first result instead of acting twice. |
Changes observed during successful MCP inspections.
Input schema / $defsAdded value: +{
+ "__schema0": {
+ "maxLength": 128,
+ "minLength": 1,
+ "type": "string"
+ }
+}Input schema / properties / commandId / $refAdded value: +"#/$defs/__schema0"Input schema / properties / commandId / maxLengthRemoved value: -128Input schema / properties / commandId / minLengthRemoved value: -1Input schema / properties / commandId / typeRemoved value: -"string"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds useful framing (org-scoped, an undo of a learned preference, so low blast radius), but says nothing about what happens with an unknown or already-deleted id, or whether the removal is permanent versus soft.
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?
Two short sentences, zero padding, with the core action and id source front-loaded and the undo framing used as a closing hook rather than filler.
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 two-parameter, single-required delete with full annotation coverage and no output schema, the description supplies what an agent needs: what it deletes, how to obtain the id, and why a user would invoke it. Only edge-case behavior (missing id, repeat with a different commandId) is left to the schema and annotations.
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 coverage is 100% and commandId's retry semantics are documented in the schema, so the baseline is 3. The description earns a step up by documenting the provenance of tasteId (get_profile `taste` or remember_taste), which the schema does not say.
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 and cardinality ('Delete one entry'), the exact resource ('the org's learned taste'), and the keying parameter ('by its id'). It also implicitly distinguishes itself from remember_taste and list_taste by naming where the id comes from, so an agent can separate it from siblings without opening schemas.
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?
Gives the trigger context explicitly: 'This is how the user's "undo" works,' which tells the agent when to reach for it, and points to get_profile `taste` / remember_taste as the id source. It stops short of naming an alternative or a when-not condition, but the use case is unambiguous.
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.