[AI-bot listing] KGNINJA trial catalog: low-spec AI field decision notes (single-user self-reports; no independent reproduction or current performance guarantee). Free sample OMARCHY-03 via get_experience_case or GET /cases/OMARCHY-03. Four paid cases @ 0.01 USDC on Base via x402 MCP. payTo 0x4D7d842536De9Eb491AE2300126B3CDdE7B0aDE3. Sales: https://ai-experience-catalog-20261001.fuwafuwow.workers.dev/ . No fabricated purchase stats. Browser alone cannot buy via MCP URL.
Scored across 2 tools
The two tools target distinct actions: get a single experience case versus list public previews. There is minimal overlap, and the descriptions clarify the retrieval and payment constraints.
Both names use snake_case and a verb_noun pattern: get_experience_case and list_experience_previews. The convention is consistent and predictable.
Only two tools is thin for a catalog server; basic discovery and retrieval are covered, but search, filtering, or broader listing may be expected. It is borderline rather than extreme.
The surface provides only preview listing and single-case retrieval; there is no search, filtering, full-case listing, or payment support despite paid retrieval being referenced. These gaps limit an agent's ability to discover and retrieve all catalog content.
One approved case. OMARCHY-03 is free. Four other cases require x402 payment; cached replay fails closed and requires manual support.
| Name | Required | Description | Default |
|---|---|---|---|
| case_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false. The description adds useful behavioral context beyond annotations: OMARCHY-03 is free, four other cases require x402 payment, and cached replay fails closed requiring manual support.
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 very short and front-loads the single-case scope. It uses fragmentary sentences, but every clause carries some information and there is 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 one-parameter lookup tool with no output schema, the description omits what is returned, the meaning and format of case_id, and how to handle the four paid cases. It gives some payment and failure-mode context but leaves core invocation details 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?
Schema description coverage is 0% for the required case_id parameter (string, maxLength 100). The description mentions 'OMARCHY-03' and 'four other cases,' which hints at valid values, but it never names or explains the case_id parameter, its format, or how to supply it.
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 says 'One approved case' but never states a verb like retrieve/fetch nor explains what an 'experience case' is; it only weakly implies the tool returns a single case. It does not differentiate from sibling list_experience_previews.
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?
No when-to-use guidance is provided, and the sibling list_experience_previews is not mentioned as a prerequisite or alternative. The payment notes describe cost conditions rather than when an agent should select this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Public previews and limitations. Paid retrieval is initial-delivery-only; do not repay after a lost response.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, but the description adds useful behavioral context: paid retrieval is initial-delivery-only and should not be repaid after a lost response. This is a specific operational rule beyond the annotations, though it remains somewhat cryptic about when or how it applies.
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 two short sentences with no obvious filler. The first sentence is front-loaded but vague, while the second sentence supplies a focused behavioral warning.
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, read-only listing tool with no output schema, the description is minimally adequate. It omits what the previews contain and does not clarify the relationship to the sibling get_experience_case.
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 has zero parameters and 100% schema description coverage, so the baseline score is 4. No additional parameter semantics are needed or provided.
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 names a broad subject ('Public previews and limitations') but does not state a clear verb or scope, so it is only vaguely clear that this tool lists previews. It also does not distinguish this tool from the sibling get_experience_case.
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?
There is no guidance on when to use this tool versus get_experience_case, nor any explicit usage context. The sentence 'Paid retrieval is initial-delivery-only; do not repay after a lost response' is a payment/retry warning rather than a selection guideline.
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_experience_caselist_experience_previews
Add one secure layer between your agents and this server.