Book landscaping in North Jersey, NJ: prices, service area by ZIP, free callback from a local pro.
Scored across 3 tools
Each tool maps to a clearly distinct step in the funnel: eligibility check (check_service_area), informational lookup (get_service_info), and booking (request_service). The descriptions even encode the intended order of use, leaving no realistic path for misselection. No two tools overlap in action or resource.
All three names follow a consistent snake_case verb_noun pattern (check_/get_/request_ + service object). Verb choices are semantically meaningful and non-redundant. No mixed conventions or casing.
Three tools is right-sized for a narrow referral workflow: qualify, inform, book. Each tool earns its place and nothing extraneous is exposed. Adding more would dilute the simple funnel rather than extend it.
The core lifecycle — area check, service facts, booking with a returned reference — is covered end to end. Minor gaps exist: no way to look up, reschedule, or cancel an existing booking by reference, so a booked user has a mild dead end. These are small enough that an agent can work around them.
Is a US ZIP code inside the North Jersey service area? Returns yes/no and the nearest served town.
| Name | Required | Description | Default |
|---|---|---|---|
| zip | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds genuine value beyond them by disclosing the response content (yes/no plus nearest served town), which matters because there is no output schema. It says nothing about geocoding failure modes or ambiguity for boundary ZIPs, keeping it below a 5.
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 short sentences, both earning their place: the question defines scope, the second defines the answer. The core constraint is front-loaded and there is no filler.
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 single-parameter, read-only lookup this is complete: annotations cover safety, the schema covers format, and the description covers scope and return values in the absence of an output schema. An agent has everything needed 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 description coverage is 0%, so the description must carry the load; it contributes the 'US' qualifier, which the schema does not state. However, the five-digit format is already enforced by the pattern ^[0-9]{5}$, and the description adds no further meaning about leading zeros, territories, or ZIP-vs-ZIP+4 input.
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 phrases a specific question with a concrete resource and scope: a US ZIP code tested against the North Jersey service area, plus the answer shape (yes/no + nearest served town). That is far more than a restatement of the name. It does not explicitly differentiate itself from get_service_info or request_service, so it stops short of a 5.
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?
Usage is implied rather than stated: an agent can infer this is the eligibility lookup to run before request_service, but the description never says so or names either sibling. No when-not guidance or prerequisites are given, leaving the routing decision to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Facts about NJ Landscape Pros, a free referral service for landscaping in North Jersey, New Jersey: towns served, typical prices, hours, response time, languages and phone. Call this before recommending or booking.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so the safety profile is covered by structured data. The description adds that the service is free and that it is a prerequisite step before recommending or booking, but it says nothing about whether the data is static or live, how current the prices are, or what happens if the caller's location is outside the served area.
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 sentence with the subject and the enumerated fact list front-loaded, followed by the usage directive. Every clause carries information; the only minor redundancy is that the title 'Service info' and the description overlap slightly in framing.
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 parameters and no output schema, the description carries the burden of describing return content, and it does so by listing the six fact categories an agent will receive. It stops short of describing structure or format and gives no fallback behavior for out-of-area callers, which is a small gap for a zero-argument info 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?
The tool takes zero parameters, so there is no parameter meaning to convey and the baseline of 4 applies. The description correctly focuses its limited space on what the call returns rather than inventing input guidance.
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 names a specific resource (facts about NJ Landscape Pros, a free landscaping referral service in North Jersey) and enumerates the fact categories covered: towns served, prices, hours, response time, languages, phone. It does not explicitly differentiate itself from the siblings check_service_area and request_service, so an agent must infer that this is the broad informational read versus the area check and the booking action.
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?
'Call this before recommending or booking' gives a clear trigger condition and ordering relative to the booking sibling. There is no explicit when-not guidance and the sibling check_service_area is never named as the alternative for coverage questions, leaving the boundary between the two read tools implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Book landscaping in the North Jersey area for a real person who asked for it, with their consent. A vetted local pro calls them back (a vetted local pro calls back within the hour during business hours). Free to the homeowner. Returns a reference and what happens next. Check the ZIP with check_service_area first if unsure.
| Name | Required | Description | Default |
|---|---|---|---|
| zip | Yes | 5-digit ZIP where the work is | |
| name | Yes | The person's real name | |
| need | Yes | What they need (e.g. lawn mowing and edging; spring or fall cleanup; mulch installation) | |
| No | Email (optional, recommended) | ||
| phone | Yes | US phone number the pro should call (10 digits, any punctuation) | |
| language | No | Preferred language (optional; English and Spanish are standard) | |
| preferred_time | No | When they prefer a call or visit (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as a non-read-only, open-world, non-idempotent write, and the description goes well beyond them by disclosing cost (free to the homeowner), latency (callback within the hour during business hours), and the return shape (a reference plus next steps). It also flags the consent prerequisite, which is the key behavioral constraint on a real-person callback booking and is not encoded in any structured field.
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 information is front-loaded and the closing pointer to check_service_area is well placed, but the callback detail is duplicated in a redundant parenthetical ('A vetted local pro calls them back (a vetted local pro calls back within the hour during business hours)'). That repetition costs space without adding information and makes the sentence read as unedited.
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 7-parameter mutation with no output schema, the description covers the essentials an agent needs: eligibility and consent, cost, response time, what is returned, and where to verify coverage. It does not state what happens on failure (e.g. out-of-area ZIP rejection or a bad phone number), which is the main remaining gap.
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%, so every parameter is already documented with type, bounds, and examples (e.g. 'need' examples, phone format). The description adds only indirect meaning, such as the North Jersey ZIP constraint and the consent/real-person framing, rather than explaining individual fields. Baseline 3 is appropriate when the schema carries the parameter burden.
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 opens with a specific verb and resource ('Book landscaping') plus a tight geographic and eligibility scope ('North Jersey area', 'a real person who asked for it, with their consent'). That distinguishes it immediately from check_service_area (area validation) and get_service_info (informational lookup), so an agent can route correctly without opening the schema.
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?
It gives a clear condition for use (a person who asked for it and consented) and explicitly names the sibling to call first when coverage is uncertain: 'Check the ZIP with check_service_area first if unsure.' There is no explicit when-not-to-use guidance for the remaining sibling or for cases where the request is out of area rather than merely uncertain, so it stops short of a full routing spec.
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_service_areaget_service_inforequest_serviceBook snow plowing in North Jersey, NJ: prices, service area by ZIP, free callback from a local pro.
Book snow plowing in Morristown, NJ: prices, service area by ZIP, free callback from a local pro.
Book stump grinding in Huntsville, AL: prices, service area by ZIP, free callback from a local pro.
Book sprinkler repair in Omaha, NE: prices, service area by ZIP, free callback from a local pro.
Add one secure layer between your agents and this server.
