Novelist

Prepare a novel for the user to review

prepare_novel

Saves a novel brief to the signed-in user's Novelist account and returns review_url, a link to the Novelist novel studio with the brief filled in, plus a reference price. It does not charge anything and does not start writing: the user reviews the brief on ainovelist.app and pays there. Drafts expire after 7 days.

Input Schema

Name	Required	Description
`genre`	Yes	Required. Free text, for example "cozy mystery" or "romantasy".
`title`	No	Exact title. Omit to let Novelist invent one.
`tropes`	No	Tropes to weave in, for example "enemies to lovers".
`setting`	Yes	Required. The world, place and era of the story.
`language`	No	Language the novel is written in. Default en.
`novel_size`	No	Length. Default l. xl is not offered for every quality tier (see get_novel_options).
`references`	No	Works to use as stylistic inspiration only.
`writer_mode`	No	true prepares a writer mode novel: a World Class novel the user finishes in the Writer Studio and may publish and sell under the Novelist Writer License. It is always world_class and private (publish_to_bookstore false), and always comes as EPUB and PDF at no extra cost (output_format does not apply). Default false.
`ending_style`	No	Ending flavour. Omit to let Novelist decide.
`quality_tier`	No	Default pro. world_class is a premium tier at a higher price.
`output_format`	No	Delivered file format. Default epub.
`story_outline`	No	Plot direction. Omit to let Novelist devise the plot.
`writing_style`	No	Prose style, for example "lyrical and atmospheric".
`content_rating`	No	Maturity rating. Omit to let Novelist decide.
`main_characters`	No	Main characters with a few defining traits each.
`additional_notes`	No	Anything else the user wants.
`author_credit_name`	No	Writer mode only. The author name the book carries (a real name or a pen name; no links, emails or "Novelist"). Omit to let the user type it on ainovelist.app.
`publish_to_bookstore`	No	true lists the finished novel in the public Novelist Bookstore at a discounted price; default false keeps it private.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 30, 2026

addedInput schema / properties / author_credit_name

Added value: +{
+  "description": "Writer mode only. The author name the book carries (a real name or a pen name; no links, emails or \"Novelist\"). Omit to let the user type it on ainovelist.app.",
+  "maxLength": 80,
+  "type": "string"
+}

addedInput schema / properties / writer_mode

Added value: +{
+  "description": "true prepares a writer mode novel: a World Class novel the user finishes in the Writer Studio and may publish and sell under the Novelist Writer License. It is always world_class and private (publish_to_bookstore false), and always comes as EPUB and PDF at no extra cost (output_format does not apply). Default false.",
+  "type": "boolean"
+}

First observedOct 22, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations declare a non-read-only, non-destructive, non-idempotent, closed-world mutation, and the description adds genuinely useful context beyond them: no charge is made, generation is not started, a review_url and reference price come back, and drafts expire after 7 days. It stops short of saying what happens on repeated calls (relevant since idempotentHint=false) or whether auth is required beyond 'signed-in user'.

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

Conciseness5/5

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

Three sentences, front-loaded with what it does and what it returns, then immediately defusing the two biggest agent concerns (no charge, no writing started), then the expiry caveat. No sentence is redundant.

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

Completeness4/5

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

For an 18-parameter creation tool with no output schema, the description covers the key return values and the post-call flow, which is what an agent needs. Gaps remain around repeat-call behavior and confirmation of expiry semantics for the returned URL, but nothing essential to correct invocation is missing.

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 description coverage is 100% across all 18 parameters, including enum explanations and defaults, so the schema already carries parameter meaning. The description adds no parameter-level detail beyond a few enum hints that already live in the schema; baseline 3 applies.

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

Purpose4/5

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

The description names a specific verb and resource (saves a novel brief to the user's Novelist account) and states the return payload (review_url plus a reference price). It implicitly separates itself from get_novel_options/get_novel_status/list_my_novels by being the creation step, but never names or contrasts a sibling explicitly.

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

Usage Guidelines3/5

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

The description describes the downstream workflow (user reviews on ainovelist.app and pays there) which implies this is the pre-payment brief step, but there is no explicit 'use this when' or 'do not use this if' guidance and no routing to the sibling tools. Usage must be inferred from the flow narrative.

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

All Novelist 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?