CueFrame

Remember Taste

remember_taste

Idempotent

Save one durable style preference to the org's learned taste, with its source (the job, checkpoint or chat, plus the date). Only for a preference the user stated: a revise comment, a chat correction or an explicit "remember this"; never one-off brief content, footage facts or secrets. Tell the user what you saved and that they can say undo (forget_taste). Saving text the org already holds changes nothing. Refused, never truncated, past 2,048 bytes per entry or 4,000 characters per org, or while the owner has learned taste off; a refusal is final. get_profile returns the saved entries as taste.

Input Schema

Name	Required	Description	Default
`body`	Yes	Remember a style preference for the org. Saving text the org already holds changes nothing.
`commandId`	No	Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.

Output Schema

Name	Required	Description	Default
`entry`	No	One learned style preference: advice for agents, never enforcement.
`created`	No	False when the org already held this exact text.

Schema Changelog

Changes observed during successful MCP inspections.

Changed14 schema fields changedOct 28, 2026

addedInput schema / $defs

Added value: +{
+  "__schema0": {
+    "description": "One durable style preference, at most 2048 bytes. An org's entries together hold at most 4000 characters.",
+    "minLength": 1,
+    "type": "string"
+  },
+  "__schema1": {
+    "description": "Where it came from: the job, checkpoint or chat, plus a date.",
+    "maxLength": 256,
+    "minLength": 1,
+    "type": "string"
+  },
+  "__schema2": {
+    "maxLength": 128,
+    "minLength": 1,
+    "type": "string"
+  }
+}

addedInput schema / properties / body / properties / source / $ref
```
Added value: +"#/$defs/__schema1"
```

removedInput schema / properties / body / properties / source / description

Removed value: -"Where it came from: the job, checkpoint or chat, plus a date."

removedInput schema / properties / body / properties / source / maxLength
```
Removed value: -256
```
removedInput schema / properties / body / properties / source / minLength
```
Removed value: -1
```
removedInput schema / properties / body / properties / source / type
```
Removed value: -"string"
```
addedInput schema / properties / body / properties / text / $ref
```
Added value: +"#/$defs/__schema0"
```

removedInput schema / properties / body / properties / text / description

Removed value: -"One durable style preference, at most 2048 bytes. An org's entries together hold at most 4000 characters."

removedInput schema / properties / body / properties / text / minLength
```
Removed value: -1
```
removedInput schema / properties / body / properties / text / type
```
Removed value: -"string"
```
addedInput schema / properties / commandId / $ref
```
Added value: +"#/$defs/__schema2"
```
removedInput schema / properties / commandId / maxLength
```
Removed value: -128
```
removedInput schema / properties / commandId / minLength
```
Removed value: -1
```
removedInput schema / properties / commandId / type
```
Removed value: -"string"
```

AddedOct 22, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond annotations: discloses size limits (2,048 bytes/entry, 4,000 chars/org), refusal-not-truncation behavior, idempotency on duplicate text, owner-toggle gating, and finality of refusals. Also instructs the agent to tell the user and mention undo. Rich, non-contradictory behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core action, then constraints and the undo path. Dense with no filler, though the byte/char limits appear in both schema and description, a minor redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists so return values needn't be explained, yet the description still notes get_profile surfaces entries as `taste`. The refusal thresholds, usage scope, and undo path cover everything an agent needs to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and parameter descriptions already carry the byte/char limits and source format. The description restates some limits but adds little beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Save one durable style preference to the org's learned taste') with the source it captures. Clearly distinguishes it from siblings like forget_taste, list_taste, and get_profile by naming them for their different roles.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly defines when to use ('Only for a preference the user stated: a revise comment, a chat correction or an explicit "remember this"') and when not ('never one-off brief content, footage facts or secrets'). Names forget_taste as the undo alternative, completing the routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All CueFrame tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.