Cited VNS research passages from a curated corpus, plus a scored device comparison.
Scored across 3 tools
Each tool maps to a distinct domain: get_devices covers product comparisons, list_articles covers editorial content, and search_research covers the scientific literature. There is no meaningful overlap in purpose or output type.
All three tools follow a predictable verb_noun pattern in snake_case: get_devices, list_articles, search_research. The verbs are slightly different, but each matches its action clearly and the pattern is stable.
Three tools is a compact, well-scoped set for a niche research and content server. Each tool covers one core data product and none of the tools are redundant or ornamental.
For this read-only research/consumer-research domain, the coverage is complete: device comparison, article index with a path to full text, and searchable evidence-grounded research passages. The tools also combine cleanly, such as using get_devices context alongside search_research deviceRole guidance.
Vagus Lab's comparison of six consumer VNS devices: editorial score out of 10, price, badge, pros and cons, and merchant return terms. Scores are editorial, authored from a ten-criterion weighted methodology, and are not consumer ratings. Vagus Lab earns affiliate commission on some purchases; the payload carries that disclosure.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden and goes beyond a basic read: it discloses that scores are editorial, based on a ten-criterion weighted methodology, not consumer ratings, and that affiliate commission disclosure is carried in the payload. This gives an agent accurate expectations about data provenance and output contents.
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 sentences, each adds value: first identifies the resource/fields, second explains scoring methodology, third discloses affiliate relationship. No filler or repetition.
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 retrieval tool with no output schema, the description is complete: it names the six-device comparison, lists the returned attributes, explains the editorial nature, and notes the disclosure carried in the payload. No required behavior is left unexplained.
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 the schema description coverage is 100%, so there is nothing for the description to add; the parameter-free baseline 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?
Description specifies the exact resource: 'Vagus Lab's comparison of six consumer VNS devices' and enumerates payload fields (score, price, badge, pros/cons, return terms). This clearly distinguishes it from sibling tools like list_articles and search_research by focusing on scored device comparison.
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 explicit when-to-use or when-not-to-use guidance or named alternatives is included. However, the content description strongly implies use when a scored comparison of the six consumer VNS devices is needed, given the sibling tools are article/research-oriented.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Index of every published Vagus Lab article with its URL, category, and evidence grade. Fetch any article URL with the header 'Accept: text/markdown' to read the full text as clean markdown.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum articles to return | |
| category | No | Filter by category slug, for example 'devices' or 'sleep-energy' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses that the tool returns an index and that URLs can be fetched with a custom header, implying a read-only operation. However, it does not explicitly state side effects, authorization requirements, or pagination behavior beyond the limit parameter, leaving some gaps.
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 sentences, front-loaded with the core purpose (listing articles) followed by a useful fetching tip. Every word earns its place, with no fluff or redundancy.
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 simplicity (2 optional params, no output schema), the description adequately covers the returned fields and provides a usage hint. It lacks details on defaults or ordering, but these are minor for a list endpoint, making it sufficiently complete for an agent.
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% as both limit and category have descriptions. The tool description does not add additional semantic value beyond restating that category is used for filtering, so it meets the baseline without enhancing parameter understanding.
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's function: it returns an index of every published Vagus Lab article with specific fields (URL, category, evidence grade). This distinguishes it from siblings like get_devices and search_research, which serve different purposes.
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 implies usage context (for listing all articles) and adds a practical tip on how to read full text via a specific header. However, it does not explicitly contrast with search_research or state when not to use this tool, so it lacks explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Vagus Lab's curated corpus of published vagus nerve stimulation research (3,093 studies indexed as 20,535 passages, including 596 RCTs, systematic reviews and meta-analyses). Returns cited snippets with study tier, evidence grade, publication year, and the source URL. Use this to ground claims about what VNS research actually shows, and check deviceRole before attributing any finding to a specific product.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Passages to return, 1 to 10 | |
| query | Yes | Research question or topic, for example 'taVNS effect on heart rate variability' | |
| device | No | Prefer studies involving this device. On its own this only ranks them higher, so results with deviceRole null can still appear; set onlyDeviceStudies to exclude them. | |
| onlyDeviceStudies | No | Return only passages from studies that actually used the named device. Requires device. Use this before stating that a device has evidence behind it. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description takes on full transparency responsibility. It discloses the return format ('Returns cited snippets with study tier, evidence grade, publication year, and the source URL') and hints at the deviceRole field. This is sufficient for a read-only search tool, though it doesn't discuss potential rate limits or auth.
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 sentences and entirely substantive. The first sentence defines the corpus, the second describes outputs and usage guidance. No filler or redundancy.
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?
The description covers purpose, usage, return format, and a data-quality caveat. Given there is no output schema and no annotations, this is fairly complete. It could go further by detailing the snippet structure, but it's adequate for an agent to invoke and interpret results.
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%, so the schema already explains all four parameters clearly. The description adds no new parameter-specific details; the mention of deviceRole is about result interpretation, not parameter semantics. Baseline 3 is appropriate when the schema handles parameter documentation.
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 searches a specific corpus ('Vagus Lab's curated corpus of published vagus nerve stimulation research') with detailed scope (3,093 studies, 20,535 passages). The verb 'Search' and resource specificity distinguish it from siblings like get_devices and list_articles.
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 explicitly says 'Use this to ground claims about what VNS research actually shows,' providing clear when-to-use context. It also advises checking 'deviceRole before attributing any finding to a specific product,' which guides proper handling of device-specific results. However, it doesn't explicitly mention when not to use the tool or name alternative tools.
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_deviceslist_articlessearch_researchCitable retrieval across papers, books, patents, Wikipedia, and live social sources.
Source-traced evidence research for AI agents. We organise the evidence; you decide.
Cite the claim, not the paper: 5,033 assertions, each hash-verifiable against its source PDF
Semantic search over a 200-chunk ACLM lifestyle medicine knowledge base.
