search_studiesSearch EBI BioStudies — a keyless database of biological study descriptions that links across EBI archives (ArrayExpress, PRIDE, etc.). Find studies by keyword and get accession, title, authors, type, release date, and link/file counts.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number, default 1. | |
| limit | No | Max results per page, default 15, max 100. | |
| query | Yes | Keyword query, e.g. "crispr" or "breast cancer". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description adds behavioral context beyond annotations: 'keyless database' implies no authentication needed, 'links across EBI archives' clarifies scope, and it lists returned fields. Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so description complements them.
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 core purpose and additional details. No redundant phrases; every sentence adds value.
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?
Without an output schema, the description adequately explains return fields (accession, title, etc.). It could mention pagination defaults or results format, but schema covers pagination params. Overall sufficient for a search tool with strong annotations.
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 100% with all three parameters described. The description adds no additional parameter semantics beyond what the schema provides (e.g., 'keyword' for query). Baseline 3 is appropriate.
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 clearly states verb 'Search' and resource 'EBI BioStudies database', specifies linking across archives, and lists returned fields. Distinguishes from siblings like 'get_study' which retrieves a single study.
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 (searching biological studies via keyword) but does not explicitly state when to use this tool over alternatives or exclude scenarios. No mention of when-not-to-use or comparison with sibling search tools.
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.
Several tools occupy nearly identical roles: ask_pipeworx and ask_pipeworx_beta are described as functionally identical right now, ask_pipeworx_grounded and deep_research are overlapping query modes, and ai_visibility_check / scan_competitor_ai_presence / discover_tools / suggest_questions all blur into discovery or visibility tasks. The two actual BioStudies tools are clear, but they are buried in a server dominated by Pipeworx meta-tools.
All tool names use snake_case, and many follow a verb_noun shape such as search_studies, get_study, and discover_tools. However, the convention is inconsistent across the set: noun-first names like entity_profile and polymarket_edges, brand-prefixed names like pipeworx_feedback, and verb-first product names like ask_pipeworx all coexist, making the pattern harder to predict.
33 tools is well into the too-many range, and the count is especially inappropriate for a server named Biostudies since only search_studies and get_study actually belong to that domain. The rest form a sprawling general-purpose data-research platform that appears to have been merged into one server without a clear scope.
For the BioStudies-specific surface, search_studies and get_study provide reasonable read-only coverage for the EBI archive. But as the broader research platform the other 31 tools imply, the set is hard to evaluate for completeness because most actual data access is delegated to Pipeworx's hidden 5,718 tools rather than exposed directly, leaving notable gaps in transparency and direct source-level control.