claidex_tool_catalogReturn the complete MCP tool catalog, optionally including full input schemas and filtering native versus agent-backed tools.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | all | |
| include_schemas | Yes | Include full JSON Schemas in the catalog. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full behavioral disclosure burden. It states the tool returns a complete catalog and supports filtering, but it does not disclose the return format, whether the catalog includes descriptions, the potential size of the output, or what 'complete' means. It also leaves the terms 'native' and 'agent-backed' undefined, which could confuse the agent.
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 a single sentence with the primary action ('Return the complete MCP tool catalog') front-loaded. It adds relevant optional details in a compact manner without any redundant words. Every phrase contributes to the understanding of the tool's functionality.
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 that there is no output schema, the description should clarify the structure of the returned catalog (e.g., list of tool names, descriptions, metadata). It does not. Also, the schema marks both parameters as required despite having defaults, and the description does not explain behavior when defaults are used. This leaves important operational gaps for the 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?
The schema description coverage is only 50% (include_schemas has a description, source does not). However, the tool description compensates by explicitly referencing 'full input schemas' for include_schemas and 'filtering native versus agent-backed tools' for source, effectively clarifying the purpose of both parameters. This goes beyond the schema and provides meaningful semantic mapping.
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 action: 'Return the complete MCP tool catalog.' It also specifies two optional capabilities (including full input schemas and filtering by source), which precisely distinguishes this tool from the sibling tools that are domain-specific search or query tools. The verb 'return' plus the resource 'MCP tool catalog' makes the purpose unambiguous.
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 does not provide any when-to-use guidance or comparison with alternative tools. It does not mention exclusions, prerequisites, or situations where this tool should be preferred over siblings. The catalog nature implies a discovery use case, but the agent is left to infer this from the tool name and sibling context rather than explicit guidance.
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 have overlapping responsibilities: search, search_claims, search_preprint_flags, and claidex_claim_risk_matrix all query claim/failure data, while rank_documents_by_embedding and rerank_documents both perform relevance ranking. The compatibility-oriented fetch/search tools add further confusion because their names collide with fetch_research_url and search_claims.
Names are grouped by prefixes (claidex_, query_, search_, run_) but the groups use different conventions, and bare verbs like 'fetch' and 'search' sit alongside prefixed forms like 'fetch_research_url' and 'search_claims'. The pattern is readable but not uniform.
24 tools is at the heavy end for an MCP server; while the breadth reflects many biomedical data sources and utilities, the count includes several meta/compatibility tools that could be consolidated. It is borderline but not unreasonable.
The surface covers the core biomedical workflows: searching claims, retrieving full claim content, querying failure graphs, checking preprints, and looking up drugs/trials/targets/adverse events. Minor gaps exist, such as no direct way to fetch a single clinical trial by ID beyond the search function, and no write/update operations for claims, but these are likely outside the read-only research scope.