Search public dataset, software, article, method and experiment listing metadata by title, summary, question, comparison, use case, source identity, rights and limits. Results retain source revision and readiness; they are not scientific evidence.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | ||
| page | No | ||
| limit | No | ||
| query | No | Words matched across public listing metadata. | |
| rights | No | ||
| collection | No | Exact public collection ID. |
Changes observed during successful MCP inspections.
Input schema / properties / collectionAdded value: +{
+ "description": "Exact public collection ID.",
+ "type": "string"
+}Input schema / properties / pageAdded value: +{
+ "default": 1,
+ "maximum": 10000,
+ "minimum": 1,
+ "type": "integer"
+}Input schema / properties / query / descriptionPrevious value: -"Words matched against titles."New value: +"Words matched across public listing metadata."Input schema / properties / query / maxLengthAdded value: +300Input schema / properties / rightsAdded value: +{
+ "enum": [
+ "evidence_recorded",
+ "needs_review"
+ ],
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It discloses two useful traits ('Results retain source revision and readiness; they are not scientific evidence'), but says nothing about pagination, result ordering, or typical return size, which matters for a paged search tool with page/limit params.
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?
One dense sentence but appropriately scaled to a search tool's scope. It front-loads the searched resources and adds the evidence caveat at the end.
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 6-param, paged search tool with no annotations and no output schema, the description omits result format, pagination semantics, and enum meaning. The two sentences are a start but leave significant gaps.
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 33%, with 6 params, so the description must compensate. It loosely maps query to 'title, summary, question, comparison, use case' fields for kind, rights, collection, and the two enums, but page, limit, and the enum values are not explained. This falls short of the 3 baseline.
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 (search) and the searched resource type (public dataset, software, article, method, experiment listing metadata), plus the fields matched. This is clear but the vague catch-all 'resource' in the name and the absence of a sibling-naming distinction (e.g., vs. get_resource or search_public_preprints) keeps it from a 5.
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 no when-to-use guidance and no alternatives, despite a crowded sibling list containing get_resource and search_public_preprints. An agent has to infer what this covers that get_resource does not.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.