Skip to main content
Glama

Idiolect AI

by app.idiolect

Write

write

Create a new piece of writing for the user. Start with the request and facts already available; a short request is enough. Idiolect AI applies the user's established writing patterns automatically. If more personal writing is needed, this tool returns the precise shortfall so you can find only that evidence, obtain permission to store it and retry the same task. Do not check profile state first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
formatNoThe kind of finished piece when the user has made it clear. Omit this when it is not clear; the writing task can still proceed.
requestYesWhat the finished piece should do. Carry forward the audience, purpose, facts and constraints already present in the user's request. A short request is enough. Do not invent facts merely to make it feel more complete.
evidenceNoUse only after this writing tool says personalization needs more evidence. Include the exact natural writing the user actually authored and has explicitly agreed Idiolect AI may store for personalization. Prefer the smallest trustworthy set from a writing situation close to the current task; broaden only when needed. Exclude prompts, AI-written text, templates, boilerplate, signatures, quoted or forwarded text and anything with uncertain authorship.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
nextYes
textNoThe finished writing. Present only when status is complete.
errorNo
statusYesWhere the original writing task stands: finished, waiting for approved writing evidence, ready for the same task to be retried, still preparing personalization or unable to complete.
messageYesA concise explanation of what happened and, when needed, the exact next step.
neededWritingNo
omitEvidenceOnRetryNoTrue when approved evidence has been accepted and the same writing task should now be retried without sending that evidence again.

TDQS

A4.4/5.0
Behavior4/5

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

Annotations provide little behavioral signal beyond readOnly=false and destructive=false. The description adds that Idiolect AI applies the user's writing patterns automatically, that insufficient personalization produces a precise shortfall, and that the caller should collect evidence, obtain permission, and retry. This is meaningful behavioral context beyond the structured fields.

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?

Four sentences, roughly 80 words, with the purpose front-loaded and every sentence earning its place. It covers the basic call, the personalization behavior, the evidence retry loop, and a direct do-not-check instruction without repeating schema content.

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?

It covers the full workflow: initial request, automatic personalization, shortfall detection, evidence collection with permission, and retry. An output schema exists, so return-value details are not required. The main omission is an explicit routing statement against the rewrite sibling, but that is a moderate gap given the otherwise complete guidance.

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?

The input schema already documents all parameters fully, including the evidence consent rules, so the baseline is 3. The description adds cross-cutting guidance: a short request is sufficient, facts should not be invented, and evidence should only be gathered after the tool reports a shortfall. This pushes it above baseline.

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?

The description opens with a concrete verb and resource: 'Create a new piece of writing for the user.' The word 'new' distinguishes it from the sibling tool 'rewrite', making the tool's role clear without needing to name the alternative.

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?

It gives clear practical guidance: start with the request and facts already available, keep the request short, and do not check profile state first. It also explains the retry flow when more personal evidence is needed. It does not explicitly compare with rewrite or state when not to use this tool, so it stops short of a 5.

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

All Idiolect AI toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation5/5

The two tools are clearly distinct: 'write' creates new text while 'rewrite' modifies supplied prose. Each description explicitly states the different input and purpose, leaving no ambiguity about which tool to select.

Naming Consistency5/5

Both tool names are single lowercase verbs that form a natural pair: write and rewrite. The naming is simple, predictable, and consistent in style.

Tool Count3/5

Two tools feel minimal for a writing assistant, but the server's scope is tightly focused on generating and revising text. It is borderline rather than severely underprovisioned.

Completeness4/5

The core creation and revision workflows are covered, and the integrated profile shortfall mechanism handles personalization. A minor gap is the lack of any tool to manage or inspect the writing profile directly, but agents can work around it.

Resources