Find checked US roofers, siding and gutter contractors by city. Read-only, no login.
Scored across 2 tools
The two tools have clearly distinct purposes: retrieval by id versus location-based search. An agent can easily determine which to use based on whether it has an id or a location.
Both use a consistent verb_noun pattern (get_contractor, search_contractors) with the same resource noun. Predictable and readable.
Only 2 tools is thin for the stated directory purpose. A reasonable minimum (search + get), but leaves little flexibility for filtering, listing by category, or batch retrieval.
Search plus get covers the core read workflow, but there are notable gaps: no way to list by specialty or rating filters, no pagination/result-count control, and no batch fetch for multiple ids, which agents will hit in practice.
Get one contractor from The Roofing List by id. Returns nothing for a business that is closed or no longer listed.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The contractor id from search_contractors. |
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| city | Yes | |
| name | Yes | |
| phone | Yes | |
| state | Yes | |
| rating | No | From reviews published on The Roofing List only. Absent when there are none. |
| trades | Yes | |
| claimed | Yes | |
| website | No | Only present for claimed profiles. |
| profileUrl | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine value beyond that by disclosing the null-result semantics: nothing is returned for a closed or delisted business, which an agent could otherwise misread as an error. It does not go further (e.g., error vs empty distinction, auth requirements).
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, zero filler, with the core action front-loaded and the edge-case caveat second. Nothing to trim.
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 an output schema present, the description need not explain the returned record, and it correctly covers the empty-result case. The only gap is the absence of any usage/routing context relative to search_contractors, which would make it fully self-sufficient.
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?
Only one parameter and schema description coverage is 100%, so the schema already fully explains 'id' as coming from search_contractors. The description adds no syntax, format, or range detail beyond the schema, so the baseline 3 applies.
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 ('Get one contractor from The Roofing List by id'), which is clear and unambiguous. The singular 'one contractor ... by id' implicitly distinguishes it from the sibling search_contractors, but the description never names or contrasts with that sibling explicitly, so it falls 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?
There is no explicit when-to-use statement, no exclusions, and no named alternative (search_contractors is only referenced inside the schema's id parameter, not the description). Usage is only inferable from the phrase 'by id', which is thin guidance for a lookup tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find roofing, siding or gutter contractors in a US city, or near a US ZIP code, from The Roofing List. Give city and state, or zip. A zip returns the nearest firms within 25 miles, nearest first. Returns only listed businesses that are open and passed our contact check. Ratings come from reviews published on The Roofing List only.
| Name | Required | Description | Default |
|---|---|---|---|
| zip | No | A 5-digit US ZIP code, for example "78701". Returns the nearest firms within 25 miles, nearest first. With zip, city and state are ignored. | |
| city | No | US city name, for example "Austin". Give city and state, or zip. | |
| limit | No | How many results, 1 to 25. Default 10. | |
| state | No | US state as a USPS code ("TX") or a full name ("Texas"). Give city and state, or zip. | |
| trade | Yes | The trade: roofing, siding or gutters. |
| Name | Required | Description |
|---|---|---|
| contractors | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive and closed-world, so the description earns credit for adding genuine behavior: a zip search is a 25-mile radius, results are nearest-first, and only businesses that are open and have passed a contact check are returned. The note that ratings come solely from reviews published on The Roofing List is valuable provenance context an agent would otherwise assume wrong.
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?
Four sentences, front-loaded with purpose, then location rules, then result semantics and provenance. Slight redundancy with the schema on the 'give city and state, or zip' rule, but nothing is padding.
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?
An output schema exists and annotations carry the safety profile, so the description only needs to explain search behavior, which it largely does: radius, ordering, eligibility filter, and data provenance. It stops short of saying what an empty result set looks like or whether results are capped by anything other than limit, but nothing critical to a correct call is missing.
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% and already documents the zip/city/state trade-off, the ZIP pattern, and the 1-25 limit with a default of 10. The description restates the city-or-zip rule and the trade options but adds no format or precedence detail beyond the schema, so the baseline 3 applies.
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 (find), the resource (roofing/siding/gutter contractors), the geographic scope (US city or ZIP), and the data source (The Roofing List). The enumerated trades and geography make it immediately distinguishable from a by-ID lookup like get_contractor.
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 tells the agent how to supply the location criterion ('Give city and state, or zip') and implicitly that zip takes precedence, which is useful calling guidance. However, it never addresses the sibling get_contractor or states when this tool should be preferred over a direct record lookup, so the when-versus-alternatives dimension is left to inference.
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.
search_contractors4 fields changedInput schema / properties / city / descriptionPrevious value: -"US city name, for example \"Austin\"."New value: +"US city name, for example \"Austin\". Give city and state, or zip."Input schema / properties / state / descriptionPrevious value: -"US state as a USPS code (\"TX\") or a full name (\"Texas\")."New value: +"US state as a USPS code (\"TX\") or a full name (\"Texas\"). Give city and state, or zip."Input schema / properties / zipAdded value: +{
+ "description": "A 5-digit US ZIP code, for example \"78701\". Returns the nearest firms within 25 miles, nearest first. With zip, city and state are ignored.",
+ "pattern": "^\\d{5}$",
+ "type": "string"
+}Input schema / requiredPrevious value: -[
- "trade",
- "city",
- "state"
-]New value: +[
+ "trade"
+]get_contractorsearch_contractorsHire evidence-verified home-service contractors. Confirmed-job reviews only; rank is never buyable.
Search licensed US contractors by trade or location, fetch profiles and reviews, and submit leads.
Find owner-operated plumbers, HVAC techs, electricians and roofers in OK, KS, NE, IA and MO.
Find and verify trustworthy US home-services contractors by their un-buyable HomeClip Trust Score.
Add one secure layer between your agents and this server.
