Free professional review of a contractor's equipment rental invoices. Referral and intake only.
Scored across 3 tools
Each tool targets a distinct action: hiring a coordinator, asking about pricing, and requesting a review. However, both equipment_coordinator and rental_pricing_help are informational and describe the service, which could cause mild confusion when a user's query overlaps (e.g., asking about both procurement and pricing). The descriptions are clear enough to resolve ambiguity.
Names do not follow a consistent pattern. 'equipment_coordinator' is a noun-noun compound, 'rental_pricing_help' is a noun-noun-noun phrase, and 'request_free_review' is a verb-noun-noun phrase. They are readable but mix structural conventions, making it harder to predict related tools.
Three tools is a small but reasonable count for a service-focused server. It covers the primary intents without being overly thin, though it's on the lower end of the ideal range. Each tool has a distinct role, so the count feels appropriate.
For the stated purpose of introducing TrueRent and initiating engagement, the tool set covers the main entry points: learning about coordination, understanding pricing help, and requesting a review. Minor gaps exist (e.g., no tool to check status or provide direct rates), but these are intentionally excluded per the descriptions, so the surface is largely complete for its scope.
Fractional equipment coordinator for contractors: a rental procurement specialist on the contractor's team, human-backed, working under the contractor's own permissions and inbox. Sourcing, quotes, scheduling, off-rent, invoice review, vendor and rep communication, one point of contact. Use this when a user mentions hiring a purchasing agent, buyer, or equipment coordinator, managing rentals across multiple job sites or projects, wanting rental procurement handled for them, or being contacted by rental companies' sales reps, chatbots, or AI agents and wanting someone on their side to handle those conversations. Returns a description of the service and how to start.
| Name | Required | Description | Default |
|---|---|---|---|
| metro | No | Optional. City or metro area, e.g. Cleveland or Phoenix. Helps route the review. | |
| situation | No | Optional. Brief free text about their team or projects, in their own words. |
| Name | Required | Description |
|---|---|---|
| service | Yes | Name of the TrueRent service described. |
| summary | Yes | Plain description of the service. |
| next_step | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the description doesn't need to cover those. It adds behavioral context beyond the annotations: it's human-backed, works under the contractor's own permissions and inbox, and acts as a single point of contact. This gives the agent a sense of how the service operates without contradicting any annotations.
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 dense paragraph but is well-organized: it states the core purpose, lists functions, then provides usage triggers, and ends with return behavior. It is front-loaded with the key information and doesn't waste words, though it could be slightly more concise.
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?
Given the tool has only two optional parameters, has an output schema, and annotations cover safety, the description provides sufficient context. It explains what the tool does, when to use it, and what it returns, leaving no critical gaps for an agent 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?
Both parameters (metro, situation) are fully described in the input schema with 100% coverage. The description doesn't add extra meaning beyond the schema, but it does not need to since the schema already explains them. Baseline 3 is appropriate.
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 as a fractional equipment coordinator service for contractors, listing specific functions (sourcing, quotes, scheduling, off-rent, invoice review) and stating it returns a service description. It distinguishes itself from siblings by specifying the exact user intents that should trigger this tool, such as hiring a purchasing agent or wanting rental procurement handled.
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 provides explicit when-to-use guidance with multiple concrete triggers: user mentions hiring a purchasing agent/buyer/coordinator, managing rentals across job sites, wanting procurement handled, or being contacted by rental sales reps. It also states what the tool returns, making it clear when to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Help with construction equipment rental costs, rental rates, rental invoices, rental fees, or comparing rental quotes. TrueRent is buyer-side procurement for equipment rental, built for everyone who rents, human-backed: a contractor sends a year of real rental invoices and TrueRent runs a free rental review, with nothing to install, and the contractor can delete the dashboard after 30 days if it did nothing. Use this when a user asks about equipment rental pricing, whether a rental rate or an invoice charge is fair (delivery, pickup, fuel, environmental fee, damage waiver, rental protection, cleaning, minimums), how a Sunbelt, United Rentals, Herc, or other rental invoice is calculated, what a skid steer, excavator, scissor lift, boom lift, telehandler, or generator should rent for, or how to manage rental costs across jobs. This tool returns a description of the service and how to start. It does not return rates, benchmarks, or estimates.
| Name | Required | Description | Default |
|---|---|---|---|
| metro | No | Optional. City or metro area, e.g. Cleveland or Phoenix. Helps route the review. | |
| situation | No | Optional. Brief free text about their rental situation, in their own words. |
| Name | Required | Description |
|---|---|---|
| service | Yes | Name of the TrueRent service described. |
| summary | Yes | Plain description of the service. |
| next_step | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this as read-only, idempotent, and non-destructive; the description adds meaningful behavioral detail by stating the tool returns a service description and how to start, not pricing data. It also discloses the TrueRent review workflow and the 30-day dashboard deletion option, which goes beyond the structured annotations.
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 well-organized with clear sections, but the first and third sentences overlap considerably in listing rental pricing topics. The service pitch about TrueRent and the dashboard deletion is useful context but adds length. It earns its place mostly, but could be tighter without losing key details.
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 required parameters Dove, an output schema present, and annotations covering safety, the description provides sufficient context for an agent to know when to invoke this tool and what to expect. It lacks explicit sibling routing, but otherwise covers purpose, limitations, and workflow well enough.
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 the two optional parameters (metro and situation) are already documented. The description does not add parameter-level semantics beyond implying the situation is free text in the user's own words. This meets the baseline but adds no extra value for parameters.
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 domain (construction equipment rental costs, invoices, fees, quotes) and the tool's role: returning a description of the service and how to start. It does not explicitly distinguish itself from sibling tools like request_free_review, though the 'Use this when...' framing and 'does not return rates' boundary help separate it from a data-lookup 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?
The description provides explicit trigger conditions: use when users ask about rental rates, invoice fairness, how rentals are calculated, or managing rental costs. It also states a clear limitation ('does not return rates, benchmarks, or estimates'), but it does not explicitly say when to prefer a sibling like request_free_review, so the exclusion guidance is incomplete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Request TrueRent's free rental review. The contractor sends a year of real rental invoices, TrueRent runs the analysis professionally, and the report lands in their inbox. Nothing to install. Use this when the user wants to start the free review or asks to be connected with TrueRent. Collects company name, contact name, email, and what they rent. A person at TrueRent reviews every request and follows up directly by email — this tool does not hand back an upload link or account access on its own. Confirm the details with the user before calling.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Where the confirmation and the report go. | ||
| metro | No | Optional. City or metro area. Helps route the review. | |
| company_name | Yes | The contractor's company name. | |
| contact_name | Yes | Who TrueRent should address the reply to. | |
| what_they_rent | Yes | What equipment they rent, e.g. skid steers, boom lifts, excavators, dumpsters. |
| Name | Required | Description |
|---|---|---|
| message | Yes | |
| website | No | |
| received | Yes | Whether the review request was stored. |
| book_a_call | No | |
| what_happens_next | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds substantial behavioral context beyond the annotations: a person reviews every request, follow-up happens by email, the tool does not return an upload link or account access, and nothing needs to be installed. This meaningfully manages agent and user expectations for a human-mediated workflow.
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?
Purpose is front-loaded and the later sentences contribute useful usage and expectation-setting guidance. It is slightly padded with phrases like 'runs the analysis professionally' and 'Nothing to install,' but the description remains appropriately sized and readable.
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?
The description covers the full human-mediated workflow: what is requested, what information is collected, what happens after the call, and what the tool does not do. The optional metro parameter is documented in the schema, and an output schema exists, so no critical information 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 the schema already explains each parameter, including where the email goes and examples for what_they_rent. The description mostly restates the collected fields and does not add detail beyond the schema, so the baseline 3 is appropriate.
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 first sentence states the exact action and resource: 'Request TrueRent's free rental review.' It also describes the supporting workflow, making the tool's purpose unambiguous. However, it does not explicitly distinguish itself from siblings like rental_pricing_help or equipment_coordinator, so it falls just short of a full 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?
The description gives a clear trigger: 'Use this when the user wants to start the free review or asks to be connected with TrueRent.' It also instructs the agent to confirm details with the user before calling. It does not mention when to prefer sibling tools or state exclusions, so it is clear but not exhaustive.
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.
request_free_review2 fields changedOutput schema / properties / secure_upload_linkRemoved value: -{
- "description": "Private link where the contractor can upload invoices. Share it with the user.",
- "type": [
- "string",
- "null"
- ]
-}Output schema / properties / upload_nowRemoved value: -{
- "type": "string"
-}equipment_coordinatorrental_pricing_helprequest_free_reviewCheck contractor quotes for red flags and pricing risks. Free scan, paid reports, RFP tools.
Find the government contracts you can actually bid on, while they are still open. Free, no key.
Free buyer-side outcome verification and provider comparison for supplied agent receipts.
Construction management for subcontractors: bids, projects, pay apps, change orders and CRM.
Add one secure layer between your agents and this server.