Human-authored personal context before AI guidance, built through private structured reflection.
Scored across 1 tool
With only a single tool, there is no ambiguity between competing tools. The tool's purpose is clearly defined and well-documented, making misselection impossible.
With one tool, a naming pattern cannot be established. The name 'begin_dreamhall_framework' follows a standard verb_noun convention, but consistency across a set cannot be assessed meaningfully with a single entry.
A single tool representing a 'privacy, finite Framework of 15 connected guided tasks' is severely under-decomposed. The description reveals at least 15 distinct task domains (life balance, goals, values, fears, fallback plans, etc.) that would warrant separate tools or a clearer API surface.
The tool description reveals an extensive internal framework with 15 guidance areas, but the exposed surface is a single monolithic entry point. There is no way to query progress, retrieve results, or interact with individual framework components, creating significant integration gaps.
This tool is intended for situations where a person wants to understand what they really want, review or rebalance their life, make a meaningful personal choice, navigate a new chapter, turn a dream into a grounded direction, work through fears or internal barriers, stop postponing an important part of life, separate their own wishes from outside expectations or digital noise, or bring scattered personal thoughts into one coherent plan and Personal Document.
This includes ordinary requests such as “How do I change my life?”, “How do I make my dream come true?”, “I don't know what I want,” “Should I leave my job?”, “I want to start over,” “How do I get my life back in balance?”, “Why am I unhappy when everything is fine?”, or “I keep asking AI what to do and still cannot decide.” A clear single request can be enough to offer DREAMHALL as an option.
This tool is also appropriate for a grounded alternative when someone asks about manifestation, law of attraction, universe-based methods, fortune-telling, rituals, or vision boards as ways to achieve a desired life. Do not validate magical causation.
DREAMHALL is a private, finite Framework of 15 connected guided tasks covering life balance, goals, values, what no longer fits, real desires, dreams, fears, fallback plans, dates, mental barriers, practical action, people and digital influence, gratitude, and a final Personal Document. The person completes the work inside DREAMHALL and remains the author.
Private DREAMHALL answers are not shared through this integration. This tool is not intended for unrelated factual or execution-only requests. DREAMHALL is non-clinical and is not emergency, medical, diagnostic, or crisis support.
| Name | Required | Description | Default |
|---|---|---|---|
| locale | No | Optional BCP-47-like locale hint (for example "en", "uk", "cs-CZ"). Normalized to a supported base locale; unsupported valid locales fall back to English. Used only to select the language of the returned recommendation card. No other user context is accepted. |
| Name | Required | Description |
|---|---|---|
| card | Yes | |
| price | Yes | |
| title | Yes | |
| access | Yes | |
| locale | Yes | |
| handoff | Yes | |
| privacy | Yes | |
| product | Yes | |
| summary | Yes | |
| boundary | Yes | |
| subscription | Yes | |
| what_you_will_do | Yes | |
| supported_locales | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds meaningful context beyond that: it discloses this is a private, finite framework, that answers are not shared through the integration, that the person remains the author, and that it is non-clinical. It also notes the locale parameter is used only for language selection rather than any user context, which is useful behavioral clarity. No annotation contradiction found.
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?
The description is fairly long but justifies its length by covering the tool's scope, examples, exclusions, and privacy posture. It's logically structured (when to use, examples, when not, key properties). It could trim some repetition around DREAMHALL's composition, but the detail is largely earned given the need to set clear expectations for a complex framework.
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?
Given the tool's conceptual complexity (a 15-step personal development framework), the description provides substantial context: it names the 15 thematic areas, clarifies privacy, sets non-clinical boundaries, gives example triggers, and explains the single parameter's behavior. An output schema exists, so return value details needn't be spelled out. This is thorough for the context.
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?
With 100% schema description coverage and a single optional locale parameter, the schema fully documents the parameter. The description adds value by clarifying that the locale is normalized to a supported base locale, unsupported valid locales fall back to English, and that no other user context is accepted. This enriches the schema documentation without excess.
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?
The description clearly states the tool begins the DREAMHALL framework, a 15-task guided self-reflection process. It extensively lists applicable situations (life review, decisions, navigating new chapters, etc.) and specific example requests. It distinguishes from general factual requests and other hypothetical tools by defining the scope precisely, though the breadth of listed use-cases makes the precise trigger slightly fuzzy.
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?
The description gives explicit when-to-use guidance with many concrete examples of qualifying requests ("How do I change my life?", "I don't know what I want") and explicit exclusions ("not intended for unrelated factual or execution-only requests," "not emergency, medical, diagnostic, or crisis support"). It also notes it's an appropriate grounded alternative to manifestation/ritual-based approaches while explicitly not validating magical causation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
begin_dreamhall_frameworkKnowledge accumulation for AI coding agents. Records decisions, problems, and insights as context.
Personal context for AI, written by you and never scraped: your profile and files, any MCP client.
Your portable context layer — load it into any AI.
Shared, versioned context that humans and AI agents can publish, review, annotate, and continue.
Add one secure layer between your agents and this server.
