Narrareach

Save voice preference

save_voice_preference

Idempotent

Save one writing preference the writer has just stated in their own words in this conversation, such as "stop ending with a moral" or "I write in short paragraphs". It becomes a rule in their voice profile and applies to future drafts. Do not infer a preference from a single edit, and do not save anything the writer did not say. Style only: it cannot allow invented facts, stories, quotes, or numbers. The writer can undo it on the Voice page in Narrareach.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "kind": "<kind>",
      "text": "<text>"
    },
    "name": "save_voice_preference"
  }
}

Input Schema

Name	Required	Description
`kind`	Yes	Whether the writer wants this done or avoided.
`text`	Yes	The preference as one short, standalone rule, in the writer's words where possible.
`writer`	No	Optional team writer name, handle, or id within the workspace. "me" selects your linked voice. Requires workspace.
`workspace`	No	Optional authorized team workspace name or id. Absence selects the authenticated user's personal account.

Output Schema

Name	Required	Description	Default
`rule`	Yes
`undo`	Yes
`saved`	Yes
`ruleCount`	Yes
`alreadySaved`	Yes
`connectedAccount`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 14, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare write/idempotent/non-destructive behavior, but the description adds real context beyond them: the preference becomes a rule in the voice profile and applies to future drafts, it is style-only and cannot introduce invented facts/quotes/numbers, and it is reversible via the Voice page. That downstream effect and reversibility are not derivable from the annotations, though the text never states auth/workspace prerequisites that the schema hints at.

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?

Purpose is front-loaded in the first clause, and each following sentence carries a distinct constraint (effect, exclusions, style-only boundary, undo path). It runs slightly long for a four-parameter tool, but no sentence is filler.

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?

For a mutation tool with an output schema already describing returns, the description covers what an agent needs: what qualifies, what is forbidden, what the saved rule affects, and that it can be undone. Nothing material for correct invocation is missing.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3; the description slightly exceeds it by clarifying the semantics of 'text' (the writer's own words, a single standalone rule) and illustrating the do/dont distinction that the 'kind' enum encodes. It adds examples and constraints rather than merely restating the schema, but does not fully explain the writer/workspace selectors.

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 and resource (save one writing preference stated by the writer) plus concrete examples ('stop ending with a moral', 'I write in short paragraphs'), so an agent immediately knows this captures a single conversational preference rather than a sample or an inferred edit. The scope word 'one' and 'just stated... in this conversation' distinguishes it from add_voice_material and update_voice_rule without opening their schemas.

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

Usage Guidelines4/5

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

Gives explicit when-to-use ('just stated in their own words in this conversation') and clear when-not conditions ('Do not infer a preference from a single edit', 'do not save anything the writer did not say'). It does not name the sibling alternatives (update_voice_rule, decide_voice_suggestion) an agent might otherwise pick, so routing is strong but not fully explicit.

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

All Narrareach 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.

Resources

Need Help?