Find male fertility testing at labs near a US ZIP code, with prices and a link to order.
Scored across 3 tools
find_labs (search by ZIP/test type) and get_lab (detail by labRef) are cleanly separated by the list-vs-detail split, and the dependency is explicitly stated. hera_facts overlaps mildly with get_lab since both mention pricing and at-home collection, but the distinction (company-level facts vs. one specific lab's record) is clear enough.
find_labs and get_lab follow a consistent verb_noun pattern with a sensible singular/plural distinction (find_labs returns a list, get_lab takes a labRef). hera_facts breaks the pattern by being a bare noun phrase with no verb, but it's a content tool where no verb naturally applies.
Three tools map cleanly to the three things this server does: search labs, inspect a lab, and answer general questions. The surface is lean but each tool earns its place; nothing is redundant.
The discovery lifecycle (find → inspect → order via external link) is covered, but there is no order placement, order status, or actual results retrieval — users asking about an existing order or their results can only get generic FAQ text from hera_facts. That is a notable gap for a fertility-lab service, though some of it may be intentionally out of scope.
Nearest labs that accept the Hera lab order, near a US ZIP code for a semen analysis, a post-vasectomy check, a semen culture, a sperm DNA fragmentation test or sperm freezing (cryopreservation), with the price, where it is paid, and a link to order online. Use for "where can I get a sperm test near me" questions.
| Name | Required | Description | Default |
|---|---|---|---|
| zip | Yes | US 5-digit ZIP code. | |
| test | No | semen_analysis (the default: a standard sperm/fertility test), post_vasectomy (a sperm check after a vasectomy), semen_culture (checking for infection), dna_fragmentation (sperm DNA damage), or sperm_freezing (banking a sample). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive, and closed-world behavior, so the safety profile is handled. The description adds value beyond that by disclosing what comes back (price, where payment is made, an online ordering link) and that results are restricted to labs accepting the Hera order — meaningful since no output schema exists.
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 core purpose is front-loaded in the first clause, but the opening sentence is a long run-on that re-lists all five test types, duplicating the enum and inflating length. The second sentence (usage cue) earns its place; the enumeration does not.
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 two-parameter read tool with no output schema, the description is nearly sufficient — purpose, inputs, and returned fields are all covered. Minor gaps remain: search radius/result count behavior and whether a Hera order must pre-exist are unstated.
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 coverage is 100%: both `zip` and the `test` enum are fully documented in the schema. The description restates the ZIP locality and re-enumerates the test types already spelled out in the enum, adding no syntax, defaulting, or edge-case detail 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?
States a specific resource ('nearest labs') with its qualifying constraint ('that accept the Hera lab order, near a US ZIP code') and names the output contents (price, where it's paid, order link). An agent can tell this is the discovery/lookup counterpart to the singular `get_lab`, though the description never names that sibling explicitly.
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?
One concrete usage cue is given: use for "where can I get a sperm test near me" questions. There is no guidance on when to prefer `get_lab` (single-lab detail) or `hera_facts`, and no exclusions or prerequisites (e.g., whether an existing Hera order is required).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Address, phone, hours, walk-in policy, at-home collection, visit instructions and prices for one lab. Pass the labRef returned by find_labs.
| Name | Required | Description | Default |
|---|---|---|---|
| labId | No | Deprecated: pass labRef instead. | |
| labRef | No | The labRef returned by find_labs for this lab. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the enumeration of returned data domains, which is genuinely useful given there is no output schema. It does not describe error/not-found behavior for an invalid ref, which is the remaining gap.
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 waste: the content summary comes first, the required input provenance second. Nothing extraneous and nothing important buried.
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?
With no output schema, the description compensates well by listing the data domains returned. A brief note on missing/invalid ref behavior would make it complete for a lookup tool, but an agent has enough to call it 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?
Schema coverage is 100%, so both parameters are documented in the schema, including the deprecation note on labId that the description omits. The description only reiterates that labRef comes from find_labs, adding no syntax or format detail beyond the structured field.
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+resource (get details for one lab) and enumerates the returned content domains (address, phone, hours, walk-in policy, at-home collection, visit instructions, prices). 'for one lab' plus the reference to find_labs clearly separates it from the sibling list tool.
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 instructs to pass the labRef returned by find_labs, which establishes the correct call sequence and prerequisite. It doesn't state when not to use it (e.g., for bulk retrieval) or what happens with a stale ref, but the positive routing is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Hera Fertility facts in its own words: what Hera is, how ordering works, price, turnaround, results, at-home collection, semen cultures, post-vasectomy checks, DNA fragmentation, sperm freezing, hormone panels, retests, insurance, refunds and changes, medical questions, privacy.
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds behavioral context by saying the facts are 'in its own words', indicating the answers use Hera's own phrasing rather than an independent summary. It also reveals the breadth of content without contradicting any annotation.
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 that names the resource before listing all supported topics. Every listed item corresponds to a valid enum value, so there is no filler. It is long but appropriately so, given the tool covers many distinct fact categories.
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 one-parameter, read-only facts tool, the description covers the full range of available topics and the nature of the content. It does not describe the exact return format, but 'facts' sufficiently implies textual answers. The lack of an output schema is not a major gap here because the tool's behavior is straightforward.
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 sole parameter `topic` is fully enumerated in the schema, and the description mostly repeats those enum values in natural language. It does add readable labels like 'at-home collection' and 'post-vasectomy checks', but it does not define the topics or explain how to map user intent to each enum value. Since schema description coverage is 0%, the description provides only marginal semantic value beyond the enum.
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 resource as Hera Fertility facts and enumerates the full topic scope, so an agent can tell what the tool returns. It does not use an explicit verb like 'returns' or 'explains', but the content is unambiguous. It is also distinct from the sibling lab-lookup tools by nature.
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 when to use the tool: whenever a user asks about Hera's services, pricing, process, results, privacy, or related topics. It does not explicitly state when not to use it or compare against find_labs/get_lab, but the topic list provides clear context for selecting it.
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.
get_lab3 fields changedInput schema / properties / labId / descriptionPrevious value: -"The labId returned by find_labs."New value: +"Deprecated: pass labRef instead."Input schema / properties / labRefAdded value: +{
+ "description": "The labRef returned by find_labs for this lab.",
+ "type": "string"
+}Input schema / requiredRemoved value: -[
- "labId"
-]find_labsget_labhera_factsCash-pay lab tests: catalog search, all-in quotes by state, draw sites by ZIP, reviewed ranges.
Find Picardo's clinician-designed blood test panels and Labcorp tests, and get an order link.
IVF prices US clinics post, cited cost estimates, state IVF insurance laws, grants open now.
Find a sleep study clinic or home sleep test near you.
Add one secure layer between your agents and this server.