Our MCP server can determine if people looking to apply for medicaid are eligible,
Scored across 1 tool
With only a single tool in the set, there is no possibility of confusing it with another tool. Its purpose—checking Medicaid eligibility and creating a CRM lead—is clearly stated and unambiguous.
The lone tool follows a clear, descriptive snake_case verb_noun pattern (check_medicaid_eligibility). There are no other names to create inconsistency against.
A single tool is thin for a domain labeled 'Eldercare Resource Planning,' which implies broader support (e.g. asset lookups, state program comparisons, follow-ups). It works as one workflow but underrepresents the apparent scope.
The surface covers only one combined action (eligibility evaluation plus lead creation) with no read, update, or delete operations and no other eldercare resources. Agents hitting any adjacent need would find no supporting tool.
Evaluate an applicant's Medicaid long-term care eligibility and create a lead in Insightly CRM. All 10 required fields (first_name, last_name, email, phone, state, marital_status, age, income, assets, home_equity) must be collected before calling this tool.
| Name | Required | Description | Default |
|---|---|---|---|
| age | Yes | Exact numeric age (e.g. 74) or bracket string ('65 - 85', 'Over 85', 'Under 65 and not disabled', 'Under 65 and disabled & receiving SSDI'). | |
| Yes | Valid RFC-compliant email address for the applicant or primary contact. | ||
| phone | Yes | 10-digit US phone number (e.g. '5551234567'). Formatted strings like '(555) 123-4567' are sanitized. | |
| state | Yes | 2-letter US state postal code (e.g. 'FL', 'CA', 'NY') or full state name. | |
| assets | Yes | Total countable liquid/financial assets excluding primary home in USD (e.g. 15000) or bracket string ('Less than $2,000', 'Between $2,000 - $5,000', 'Between $5,000 - $10,000', 'Between $10,000 - $20,000', 'Between $20,000 - $35,000', 'Between $35,000 - $50,000', 'Between $50,000 - $130,000', 'Between $130,000- $200,000', 'Over $200,000'). | |
| county | No | Optional county name or ID (defaults to statewide calculation). | |
| income | Yes | Gross monthly income in USD (e.g. 1850) or bracket string ('Less than $1,500 / month', 'Between $1,500 - $2,000 / month', 'Between $2,000 - $3,000 / month', 'Between $3,000 - $6,000 / month', 'Over $6,000 / month'). | |
| veteran | No | Veteran status of applicant or spouse. | |
| for_whom | No | Who the assessment is being completed for. | |
| last_name | Yes | Applicant or contact last name (1–100 characters). | |
| residence | No | Current living arrangement (e.g. 'At home', 'Assisted living', 'Nursing home'). | |
| first_name | Yes | Applicant or contact first name (1–100 characters). | |
| care_reason | No | Reason for seeking Medicaid long-term care coverage. | |
| home_equity | Yes | Primary home equity in USD (e.g. 250000), equity bracket string, or 'No' / 'None' / 0 if they do not own a home. | |
| is_disabled | No | Pass true if applicant is under 65 and receiving SSDI / legally disabled. | |
| marital_status | Yes | Applicant's marital status: 'single', 'married', 'divorced', 'widowed', or 'separated'. | |
| out_of_pocket_costs | No | Estimated monthly out-of-pocket medical care costs (e.g. '$3,000 / month'). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden, and it does disclose the non-obvious CRM write side effect, which is valuable. However it says nothing about reversibility, duplicate-lead handling, auth requirements, or whether the eligibility result is persisted, so the disclosure is partial rather than complete.
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, zero filler. The purpose and the CRM side effect come first, and the critical precondition follows immediately.
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 17-parameter tool with no output schema, the description should hint at what the evaluation actually returns (eligibility verdict, percentile, recommended planning path), since nothing else documents return values. It also omits what happens to the computed result versus the CRM lead, leaving a real gap for a tool of this complexity.
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 per-field format guidance, enum values, and bracket-string options already documented, so baseline 3 applies. The description reinforces the required-field gate, but adds no semantics beyond the schema's 'required' array and per-property descriptions.
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 a specific verb and resource ('Evaluate an applicant's Medicaid long-term care eligibility') and additionally discloses the side effect ('create a lead in Insightly CRM'), so the agent understands both the computation and the write. No siblings exist to differentiate from, but the purpose is 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?
Explicitly states the precondition: all 10 required fields must be collected before calling, and it enumerates them. There are no sibling tools, so no alternatives need naming; the only missing element is any exclusion case (e.g. what to do if a field is unknown).
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.
check_medicaid_eligibility
Add one secure layer between your agents and this server.