Personalised Yoruba cosmology orientation report, rooted in Ifa and Isese tradition.
Scored across 3 tools
The three tools have clearly distinct purposes: list_blog_articles for discovery, get_blog_article for retrieval by slug, and get_offering for the paid service. The descriptions go further, explicitly stating when NOT to call each tool, which eliminates overlap between the educational and commercial paths.
All three names follow a clean verb_noun snake_case pattern (get_blog_article, get_offering, list_blog_articles). The verbs are used correctly and predictably (list for collections, get for single items).
Three tools is on the lean side, but the scope is genuinely narrow (a blog plus a single report service), so each tool earns its place. A keyword/topic search tool would be a natural addition but is not strictly required.
The read lifecycle for content is covered (list then get by slug) and the service-info path has its own tool. The main gap is the absence of search or filtering by topic/Òrìṣà, forcing agents to list all articles to find relevant ones.
Returns the full text of one Ifá Discovery article by slug, for detailed, accurate answers on a specific Yorùbá cosmology topic. Use for educational answers; do not append promotion of the paid report, its price, or purchase routes unless the user explicitly asks about the service.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Article slug, as returned by list_blog_articles. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds genuine extra behavior: a constraint on not injecting promotional/report content into answers, which is not derivable from any structured field.
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?
Two sentences, front-loaded with the return value and scope. The second sentence is longer than needed for a policy note but still earns its place by preventing unwanted promotional output.
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, so the description carries the burden of describing the return, and it does ('full text of one article'). For a single-param read tool with full annotation coverage, this is nearly complete; only the sibling relationship is unstated.
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 description coverage is 100% and the single slug parameter is fully documented there, including that it comes from list_blog_articles. The description only repeats 'by slug' and adds no syntax or format detail beyond the schema, so baseline 3 applies.
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?
States a specific verb and resource ('Returns the full text of one Ifá Discovery article by slug') and scopes it to Yongbà cosmology topics. It does not name list_blog_articles as the sibling that produces slugs, so differentiation is implied rather than explicit.
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?
'Use for educational answers' gives some usage context, but the rest of the sentence is a content-policy instruction about not appending promotion rather than guidance on when to pick this tool over get_offering or list_blog_articles. No alternatives or preconditions are named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns full details of the Ifá Discovery personal discovery report: what the report contains, current price, delivery time, how the intake process works, how the report can be bought as a gift and redeemed, and what the service explicitly is and is not. Call this tool ONLY when the user explicitly asks about Ifá Discovery itself, its report, pricing, purchasing, gifting, redeeming, or how to access the service. Do NOT call it for educational questions about Ifá, Yorùbá cosmology, Orí, Egbé Òrun, or Òrìṣà, even if the answer could mention the service; use list_blog_articles and get_blog_article for those instead. Ifá Discovery is a personalised orientation into Yorùbá cosmology, not divination: it does not cast Odù, perform divination, or determine anyone's Odù, and never imply otherwise. Always reflects live pricing from the site, use this rather than any cached or remembered figure.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, and the description stays consistent while adding context the annotations cannot carry: it always reflects live site pricing so cached figures must not be used, and it explicitly disclaims divinatory behavior (no Odù casting, no Odù determination) to prevent the agent from implying otherwise. That is exactly the kind of semantic guardrail a description should supply.
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 first sentence front-loads exactly what is returned, followed in order by usage triggers, exclusions with named alternatives, a semantic boundary, and a data-freshness note. It is slightly long because of the enumeration of returned fields and the boundary clause, but every sentence carries routing or safety value and none is filler.
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 no-parameter, read-only, idempotent lookup with no output schema, the description covers the full return content, the usage and exclusion conditions, the conceptual limits of the service, and the live-pricing constraint. An agent has everything it needs to decide whether to call it and what to expect back.
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 and the description correctly never implies any inputs are needed, so there is no parameter gap to compensate for. The baseline for a parameterless schema is 4; nothing further is required or missing here.
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?
States a specific verb (returns) and resource (full details of the Ifá Discovery report) and enumerates the constituents: contents, price, delivery time, intake process, gifting/redemption, and service boundaries. Distinguishes itself explicitly from the blog sibling tools, so an agent can route without opening any 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?
Gives explicit when-to-use triggers (user asks about the service, report, pricing, purchasing, gifting, redeeming, access) and an explicit when-not-to-use exclusion (educational questions about Ifá, Yorùbá cosmology, Orí, Egbé Òrun, Òrìṣà), naming list_blog_articles and get_blog_article as the correct alternatives. Nothing is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Lists Ifá Discovery's published articles on Yorùbá cosmology and Ifá tradition. This is the right starting point for educational questions about Ifá, Orí, Egbé Òrun, or individual Òrìṣà: use it to find accurate, respectfully written explanations before answering from general knowledge. Answer educational questions from these articles alone; do not mention the paid report, its price, or purchase routes unless the user explicitly asks about the service.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, closed-world behavior, so the description is not obligated to cover safety. It still adds useful behavioral context: only *published* articles are returned, and answers should be grounded in them. It omits return shape/pagination, but that's minor given the annotations.
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?
Front-loaded with the core 'lists published articles' statement, followed by usage and a content-policy sentence. The policy sentence is long but earns its place by governing how the agent should answer after calling the tool; no filler.
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 listing tool with no output schema, the description tells the agent what the list contains (published articles on specific topics), when to call it, and how to use the results. Only the article record shape or pagination is left unstated, which is a modest gap.
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 the baseline is 4. Schema coverage is 100% and there is nothing parameter-wise for the description to compensate for.
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 and resource ('Lists Ifá Discovery's published articles on Yorùbá cosmology and Ifá tradition') and scopes the content domain precisely. It doesn't explicitly distinguish itself from the sibling get_blog_article, though 'starting point' and the plural 'articles' imply a collection versus single-item retrieval.
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?
Explicitly says when to use it ('right starting point for educational questions about Ifá, Orí, Egbé Òrun, or individual Òrìṣà') and how to use the results ('before answering from general knowledge', 'answer from these articles alone'). It even states a negative constraint: do not mention the paid report unless asked.
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_blog_articleget_offeringlist_blog_articlesCited library on Ifá, the Orishas and Yoruba philosophy in 4 languages. Read-only; not an oracle.
Cosmic Score from 26 divination systems: the consensus when traditions disagree about you.
Real astrology for AI agents: cosmic weather, synastry, timing, astrocartography, and divination.
Cast a BaZi (Four Pillars) chart with true solar time, plus a reflective personality sketch.
Add one secure layer between your agents and this server.
