get_cost_estimateReturns the cost-estimate tool URL pre-filled with the user's insurance + service if provided, plus the general copay range. The tool URL is a hand-off — the user verifies their plan there for an exact copay.
| Name | Required | Description | Default |
|---|---|---|---|
| service | No | ||
| insurance | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Even though the readOnlyHint annotation already signals safety, the description adds important behavioral context: the tool returns a URL and a general copay range, not exact pricing, and relies on the user to verify. This clarifies that the tool is a starting point rather than a final quote, going beyond what annotations alone convey.
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 two sentences with no filler. It front-loads the main action and output, then adds the critical hand-off nuance. Every sentence earns its place, and the structure is easy to scan.
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 simple read-only tool with two optional enum parameters and no output schema, the description covers the key behaviors: what is returned and the need for user verification. It does not specify what happens when no parameters are provided, but the phrase 'if provided' implies the URL is still returned without pre-filling. Overall, this is nearly complete for the tool's 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?
With schema description coverage at 0%, the description must compensate for missing parameter semantics. It mentions 'insurance + service' and 'if provided,' which conveys the role and optionality of the two parameters. However, it does not explain the meaning of the opaque service enum codes (e.g., '354092') or how to map user intent to those values, leaving a gap for the agent.
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 identifies the tool's action: it returns a cost-estimate tool URL pre-filled with optional user information, plus a general copay range. The hand-off nature is explicitly stated, and this distinguishes it from sibling tools like book_appointment or find_provider, 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 the tool is for providing a general estimate and then letting the user verify the exact copay on the returned URL. It gives clear context for when to use it, though it does not explicitly name alternatives or state when not to use it. The hand-off sentence sets the expectation for how to apply the tool result.
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.
Each tool targets a distinct action (about, book, browse, check, find, search, start) and descriptions clarify boundary cases (e.g., book_appointment vs book_matching_session, search_content vs browse_pages). Minor overlap remains between about_emora's service catalog and browse_pages' service/specialty/insurance pages, but it is unlikely to misdirect an agent.
Tool names are uniformly lowercase snake_case and mostly follow an imperative verb_noun pattern (find_provider, check_availability, get_cost_estimate). Two small deviations — about_emora and start_here — are still readable and don't undermine the overall predictable pattern.
Ten tools is squarely in the ideal range and each one serves a meaningful step in the mental-health care journey: orientation, crisis support, content search, provider matching, availability, cost estimation, and booking. There is no obvious redundancy or bloat.
The tool set covers the full discovery-to-booking funnel, including crisis triage, provider search, availability, cost estimates, and two booking paths. Minor gaps exist (no explicit reschedule/cancel or appointment-list tool), but those actions plausibly live outside this server's hand-off model.