claidex_research_promptCompose a rigorous, reusable investigation prompt that tells an MCP client which Claidex tools and resources to use.
| Name | Required | Description | Default |
|---|---|---|---|
| disease | No | Optional disease area. | |
| objective | Yes | The investigation objective to turn into a reusable MCP prompt. | |
| target_gene | No | Optional HGNC target symbol. | |
| risk_tolerance | Yes | medium |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It explains the primary action (composing a prompt) but does not state whether the tool executes tools, returns a string, or has side effects. The word 'compose' implies generation, but more detail would improve transparency.
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?
Description is a single, well-structured sentence with no redundancy. Each word contributes meaning, and the key action and object are front-loaded.
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 tool has 4 parameters, no output schema, and no annotations. The description provides the core purpose but lacks information about the return value, how inputs shape the prompt, or what makes a prompt 'rigorous'. Given the moderate complexity, the description is minimally sufficient but not comprehensive.
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 description adds no parameter-level meaning. Schema coverage is 75% (disease, objective, target_gene have descriptions), but risk_tolerance is undocumented in both schema and description. The description does not explain how objective or risk_tolerance influence the generated prompt, missing an opportunity to compensate for the coverage gap.
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 uses the specific verb 'compose' and identifies the resource as a 'rigorous, reusable investigation prompt'. It clearly distinguishes this tool from sibling research query tools by indicating it produces an MCP client prompt rather than executing research itself.
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 by stating the prompt 'tells an MCP client which Claidex tools and resources to use,' making it clear this is for prompt generation rather than direct research. However, it does not explicitly mention alternatives or when not to use it, so it falls short of full 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.