Retrieve detailed clinical trial records in batches. Use after search tools for in-depth review.
| Name | Required | Description | Default |
|---|---|---|---|
| fields | No | Specific fields to return | |
| nct_ids | Yes | NCT IDs to retrieve in batches | |
| batch_size | No | Batch size for each API call |
Changes observed during successful MCP inspections.
Input schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"Input schema / properties / batch_size / typePrevious value: -"integer"New value: +"number"Input schema / properties / fields / anyOfRemoved value: -[
- {
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- {
- "type": "null"
- }
-]Input schema / properties / fields / defaultRemoved value: -nullInput schema / properties / fields / descriptionPrevious value: -"Specific fields to return for detailed view"New value: +"Specific fields to return"Input schema / properties / fields / itemsAdded value: +{
+ "type": "string"
+}Input schema / properties / fields / typeAdded value: +"array"Input schema / properties / nct_ids / descriptionPrevious value: -"NCT IDs to retrieve in batches of 10"New value: +"NCT IDs to retrieve in batches"Output schema / (root)Previous value: -{
- "additionalProperties": true,
- "type": "object"
-}New value: +nullDoes the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. While it mentions 'batches,' it fails to explain batching mechanics (e.g., internal pagination, concurrency), error handling for invalid NCT IDs, rate limits, or return structure. The batch_size parameter in schema implies chunking behavior not described.
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 with zero waste: first establishes capability, second establishes workflow context. Front-loaded with the core action. No redundant or filler text.
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?
Adequate for basic tool selection but insufficient for a batch operation tool with no annotations. Lacks disclosure on failure modes (partial vs complete failure), return value structure, or whether it aggregates results across batches into a single response.
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%, with clear descriptions for nct_ids, fields, and batch_size. Description adds no specific parameter syntax details, but baseline 3 is appropriate when schema is self-documenting. No parameter semantics are added by the description text itself.
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 specific action ('Retrieve') + resource ('clinical trial records') + scope ('in batches'). The 'batched' modifier distinguishes it from sibling 'get_trial_details' (implied singular) and contrasts with search tools by emphasizing 'detailed records' vs searching.
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 states workflow position: 'Use after search tools for in-depth review.' This clearly positions it as a secondary fetch tool in the retrieval pipeline, though it doesn't explicitly name which specific search tools to use first.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.