Physician-reviewed medical opinions and prescriptions for AI agents.
Scored across 3 tools
Each tool has a clearly distinct purpose: listing conditions, searching knowledge base, and submitting encounters. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern using snake_case (list_conditions, search_knowledge_base, submit_encounter).
Three tools is on the smaller side but appropriate for the focused domain of medical reference and encounter submission. Each tool serves a clear function.
The core workflow (list conditions, search, submit) is covered, but missing operations like retrieving encounter history or managing submitted encounters would aid completeness.
List all conditions and medications available through Appendix
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Filter by category name (case-insensitive, e.g. 'respiratory') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true and openWorldHint=true. The description merely restates the read-only nature ('List all...') and adds no additional behavioral details such as pagination, data format, or dynamic changes. No new context beyond the annotations is provided.
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, front-loaded sentence with no filler. It communicates the essential purpose immediately and earns its place without unnecessary detail.
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 the simple nature of the tool (one optional parameter, no output schema, read-only annotations), the description is mostly complete. It states what is listed, and the schema handles filtering. However, it does not clarify what 'Appendix' refers to or describe the return structure, leaving slight room for ambiguity.
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 covers the sole parameter 'category' with an example, achieving 100% coverage. The description does not add further parameter semantics, so the baseline score of 3 is appropriate based on schema coverage.
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 verb 'List' and the resource 'conditions and medications', with a specifier 'available through Appendix'. This distinguishes it from siblings like search_knowledge_base and submit_encounter, which serve different purposes.
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 for retrieving the full list of conditions/medications, but does not explicitly mention when to prefer it over search_knowledge_base or any exclusions. The context is sufficient to infer intent but lacks explicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Appendix's medical knowledge base for clinical literature, treatment guidelines, and reference material to help the user describe their medical issue
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results to return (1-10, default 5) | |
| query | Yes | Search query (clinical topic or question) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, covering the safety profile. The description adds useful content scope but does not disclose return format, pagination, or search behavior. No contradiction with annotations.
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?
A single, front-loaded sentence contains the verb, resource, and purpose without redundancy. Every word contributes 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?
For a low-complexity search tool with complete parameter schema and helpful annotations, the description adequately covers purpose, content scope, and use case. It does not mention return value details, but the absence is not a significant gap for such a simple tool.
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% (query as clinical topic/question, limit with range and default), so the description adds no additional parameter-level detail. The baseline of 3 applies because the schema handles parameter semantics.
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 a specific verb ('Search') and identifies the exact resource (Appendix's medical knowledge base), along with the content types searched (clinical literature, treatment guidelines, reference material). This clearly distinguishes it from sibling tools like list_conditions and submit_encounter.
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 provides clear context for when to use the tool: to search clinical reference material and help the user describe a medical issue. However, it does not explicitly contrast with sibling tools or state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submit a clinical encounter letter to the Appendix physician team for review. The letter should be in Markdown format following the Appendix letter structure. Returns feedback on completeness or a checkout URL when ready. One of our board-certified physicians will personally review the submission and provide clinical guidance and a prescription if appropriate.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Clinical letter in Markdown format (500-10,000 characters) | |
| images | No | Up to 3 images to attach | |
| session_token | No | Token from a previous response to continue the same encounter |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the submission is personally reviewed by a board-certified physician, may return a checkout URL, and could result in a prescription. This goes beyond the annotations (readOnlyHint=false, openWorldHint=true) by explaining the real-world workflow and side effects. There is no contradiction with annotations.
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 three sentences long, each serving a purpose: what the tool does, what the input should be and what it returns, and what happens after submission. It is front-loaded with the primary action and contains no redundant information.
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 the tool's moderate complexity (3 optional/nested parameters, no output schema), the description covers the essential aspects: purpose, input format, return behavior (feedback or checkout URL), and the human involvement. This provides sufficient context for an agent to select and invoke the tool correctly.
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 input schema describes all three parameters with 100% coverage, so the baseline is 3. The description adds value by specifying that the query must follow the 'Appendix letter structure', which is not in the schema, and by implying that the images and session_token relate to attachment and continuation of a submission. This enriches the parameter understanding beyond the schema.
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 action ('Submit'), the resource ('a clinical encounter letter'), and the recipient ('Appendix physician team for review'). This distinguishes it from sibling tools like list_conditions and search_knowledge_base, which are read-oriented.
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 provides clear context for when to use the tool: when you need to submit a clinical encounter for physician review. It specifies the required format (Markdown following Appendix letter structure) and the expected outcome (feedback or checkout URL). It does not explicitly mention alternatives, but the sibling tool names make the differentiation obvious.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
list_conditionssearch_knowledge_basesubmit_encounterPhysicians for the agentic era. Book a US-licensed doctor: orders, prescribes, 90-day plan.
Expert review for AI agents. On-chain proof of human review.
Doctor-reviewed blood-test markers, conditions & symptoms as agent tools. EN/RU/HE. Hosted.
Supplement safety for AI agents. 1,500+ rules, NIH+FDA data, quality grading A-D.
Add one secure layer between your agents and this server.
