A persistent intention layer for AI agents. Injects a soul document into model system prompts before each session. REST API + MCP server. Auth via X-API-Key header.
Scored across 2 tools
The two tools are cleanly separated: list_intentions is a discovery/enumeration tool and get_intention is a fetch tool. Their descriptions even specify the intended call order (list first, then get), leaving no room for misselection.
Both names follow the same verb_noun snake_case pattern (list_intentions, get_intention) with a consistent domain noun. No stylistic deviations.
Two tools is thin even for a narrow content-serving domain; a list+get pair is coherent but leaves little room for anything beyond read-only retrieval. It borders on a single-purpose lookup service rather than a well-scoped toolset.
The read lifecycle (enumerate options, then fetch a document) is fully covered, and the domain doesn't obviously need create/update/delete. Minor gaps exist around customization, previewing a composed soul document, or validating a chosen session_type/tradition combination before fetching.
Fetch a ManifestYOU soul document: a short grounding text that gives an AI agent a stable character before a session begins (honest about what it doesn't know, present, not performing). Optionally draw the agent's nature from a wisdom tradition, quoted exactly from public-domain translations, and add your organization's own words. Paste the returned soul_document into your system prompt or before the first user message. Without an API key it returns a free sample: the general soul with the Tao Te Ching lineage.
| Name | Required | Description | Default |
|---|---|---|---|
| home | No | Optional: your organization's own intention or values, in your own words (up to 600 characters). Woven into the soul document. Used with tradition. | |
| tradition | No | Optional lineage the agent's nature is drawn from, with exact cited quotes. tao=Tao Te Ching (James Legge, 1891). dhammapada=Dhammapada (F. Max Müller, 1881). gita=Bhagavad Gita (Sir Edwin Arnold, 1885). bible=The Bible (King James Version, 1611). quran=The Quran (Abdullah Yusuf Ali, translation of the meanings, 1934). many_paths=Many Paths (Legge; King James Version; Yusuf Ali). attention=Attention Is All You Need (Vaswani et al., Google Brain and Google Research, 2017). Omit for the standard document. | |
| session_type | No | Session orientation. analytical=precision and decision support. creative=generative and brand work. customer_service=grounded and human-facing. general=default. | general |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it discloses meaningful behavior: the returned document type, that it draws exact public-domain quotes, and specifically that without an API key it returns a free sample (general soul with Tao Te Ching lineage). It stops short of describing rate limits or the full response structure, but the auth/key behavior and output nature are well communicated.
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 core purpose is front-loaded in the first sentence, and the remaining clauses each add distinct information (lineage content, output usage, fallback behavior). It is dense and reads as a single long block with nested parentheticals rather than separated sentences, but wastes little.
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?
There is no output schema and no annotations, so the description must cover purpose, output, and usage, which it largely does: it names the returned soul_document and tells the agent how to deploy it. The only gap is that it does not describe the full shape of the response (e.g., additional fields alongside soul_document), leaving a slight ambiguity for an agent handling the output.
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?
Schema coverage is 100%, so the schema already documents all three parameters and baseline would be 3. The description adds value beyond the schema by explaining how home and tradition combine ("your organization's own words... woven into the soul document. Used with tradition") and by characterizing the tradition lineages, giving richer semantics than the schema fields alone.
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 uses a specific verb ("Fetch") against a clearly named resource ("a ManifestYOU soul document") and immediately defines what that resource is, so an agent understands the tool without opening the schema. The singular 'fetch a document' framing also sets it apart from the sibling list_intentions without needing to name it.
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?
It gives concrete usage context: paste the returned soul_document into the system prompt or before the first user message, and implicitly targets pre-session grounding. However, it never explicitly contrasts with list_intentions or states when NOT to call it, so the alternative-selection guidance is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the session types and wisdom traditions get_intention accepts, with what each one sets. Call this to choose a session_type and tradition before calling get_intention. Needs no API key.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses that the tool needs no API key, but does not explicitly confirm read-only/non-destructive behavior, rate limits, or output format. The 'list' verb implies safety, but the disclosure is incomplete.
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?
Three short sentences, front-loaded with the purpose, then usage, then a key constraint. Every sentence earns its place and there is no waste.
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?
For a zero-parameter discovery tool with no output schema, the description provides everything needed: what it lists, why to call it, when to call it, and that no auth is required. Nothing critical is missing.
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?
The tool takes zero parameters, so parameter semantics are not applicable. Baseline 4 is appropriate; the description sensibly focuses on what it lists rather than on non-existent inputs.
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 states a specific verb (List) and resource (session types and wisdom traditions get_intention accepts), and distinguishes itself from the sibling by positioning itself as the prerequisite discovery step. An agent can tell what it returns without opening the schema.
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?
It explicitly instructs to call this tool before get_intention in order to choose a session_type and tradition. The alternative (get_intention) is named and the sequencing is unambiguous.
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.
get_intention2 fields changedInput schema / properties / homeAdded value: +{
+ "description": "Optional: your organization's own intention or values, in your own words (up to 600 characters). Woven into the soul document. Used with tradition.",
+ "type": "string"
+}Input schema / properties / traditionAdded value: +{
+ "description": "Optional lineage the agent's nature is drawn from, with exact cited quotes. tao=Tao Te Ching (James Legge, 1891). dhammapada=Dhammapada (F. Max Müller, 1881). gita=Bhagavad Gita (Sir Edwin Arnold, 1885). bible=The Bible (King James Version, 1611). quran=The Quran (Abdullah Yusuf Ali, translation of the meanings, 1934). many_paths=Many Paths (Legge; King James Version; Yusuf Ali). attention=Attention Is All You Need (Vaswani et al., Google Brain and Google Research, 2017). Omit for the standard document.",
+ "enum": [
+ "tao",
+ "dhammapada",
+ "gita",
+ "bible",
+ "quran",
+ "many_paths",
+ "attention"
+ ],
+ "type": "string"
+}list_intentionsget_intention
Add one secure layer between your agents and this server.