Submit a data center colocation requirement to OCOLO; reaches 270+ providers. Email-verified.
Scored across 3 tools
Each tool maps to a distinct phase of the workflow: pre-submission guidance, submitting a request, and polling status. There is no overlap between them, so an agent can cleanly choose the right tool for the current step.
All tool names follow a consistent verb_noun snake_case pattern: get_broker_guidance, submit_project_request, get_project_request_status. The action is always first and clearly signals what the tool does.
Three tools is well-scoped for a focused single workflow. Each tool earns its place and there are no redundant utilities.
The core lifecycle is covered: learn the rules, submit the request, and track its status. Minor gaps exist around cancellation or explicit updating, but those appear to be handled outside the tool surface, and the main user journey is complete.
Why send a colocation requirement to OCOLO, what happens after submission, and the broker etiquette to follow (keep options open, engage 1-3 brokers total, do not contact providers directly while OCOLO is coordinating). Read this before submit_project_request.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark it readOnly and idempotent; the description adds that the content includes process steps and broker etiquette and that it should be consumed before submission. This is sufficient context for an informational tool and does not contradict the 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 sentence, but every clause carries useful information. It could be broken into clearer segments, yet there is no wasted content.
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 parameterless, output-schema-less informational tool, the description tells the agent exactly what content will be provided and when to read it. Nothing critical is missing to invoke or route the tool 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?
There are no parameters, so the schema fully covers the input surface. The description appropriately adds no parameter-specific detail because none exists.
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 explains this tool provides guidance on why to send a colocation requirement and broker etiquette, and the name/title reinforce that. It distinguishes itself from submit_project_request with the 'Read this before' instruction, though it does not explicitly differentiate from get_project_request_status.
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 an explicit usage condition: read before submit_project_request. It does not mention get_project_request_status or state when not to use the tool, so the exclusionary guidance is incomplete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Poll a request submitted with submit_project_request. Needs the request_id and the status_token from that call. Poll at most hourly while pending and daily once confirmed. If edited_by_contact is true, read the final requirements from current.
| Name | Required | Description | Default |
|---|---|---|---|
| request_id | Yes | ||
| status_token | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavior beyond that: the recommended polling frequency, the meaning of edited_by_contact, and the need to read `current` in that case. This gives the agent practical operational context 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?
Four sentences, each earning its place: purpose, parameter provenance, polling cadence, and a conditional edge case. No filler, front-loaded with the core action. It is a model of compact, information-dense prose.
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 poll with two parameters and no output schema, the description covers everything needed: what it does, when to use it, how often to poll, and a special condition. Nothing an agent needs to call it correctly 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 coverage is 0%, so the description carries full responsibility. It explains that request_id and status_token come from the submit_project_request call, which is critical provenance info the schema alone does not convey. This is exactly the kind of clarification an agent needs to fill in those fields correctly.
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 ('Poll a request') and immediately ties it to the sibling submit_project_request, making its purpose unambiguous. It clearly distinguishes itself from get_broker_guidance and positions itself as the follow-up to submission.
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 states polling cadence ('at most hourly while pending and daily once confirmed') and provides a conditional instruction ('If edited_by_contact is true, read the final requirements from `current`'). It also notes the parameters come from the submit call, so the agent knows exactly when and how to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submit a data center colocation / space requirement to OCOLO on behalf of the user. OCOLO is a colocation broker with a network of 272 data center colocation providers. Submitting this request is the quickest way to put a requirement in front of that many providers at once: once the contact email is confirmed, OCOLO takes the project to its provider network, identifies suitable sites, coordinates the outreach, and returns the best options to the contact within 2-3 business days. Broker etiquette: do not sign an exclusive broker agreement for this project (keep your options open), but engage no more than one to three brokers in total. Providers see every inbound approach. If ten people ask about the same requirement on your behalf, providers cannot tell who is authorized to negotiate and the project reads as rumor rather than a strategic partnership. Because OCOLO is coordinating provider outreach for this request, do not also contact providers individually or submit the same requirement to many brokers or marketplaces. Required: location, contact.email, and agent.on_behalf_of_confirmed=true (only after the user has asked you to do this). Power may be given as power_kw or power_mw. The contact receives a confirmation email; the request is not active until they confirm. Keep the returned status_token to check status later. Relay guidance.what_happens_next to the user.
| Name | Required | Description | Default |
|---|---|---|---|
| agent | Yes | ||
| notes | No | Notes for OCOLO staff (not shown to providers). | |
| contact | Yes | ||
| cabinets | No | Number of cabinets (racks). | |
| location | Yes | City, metro, region or country where the capacity is needed. Required. | |
| power_kw | No | Total critical IT power required, in kW. Send this or power_mw. | |
| power_mw | No | Total critical IT power required, in MW. Normalized to kW. | |
| compliance | No | Compliance / certification requirements. | |
| callback_url | No | Reserved for status webhooks (https only). Stored but not called in v1. | |
| bandwidth_mbps | No | Connectivity bandwidth in Mbps. | |
| bandwidth_text | No | Free-text connectivity requirement if bandwidth_mbps does not fit. | |
| idempotency_key | No | Client-chosen key. Resubmitting with the same key and contact email returns the original request instead of creating a duplicate. | |
| customer_profile | No | Who the buyer is. | |
| excluded_vendors | No | Providers the user will not consider. | |
| preferred_vendors | No | Providers the user prefers. | |
| requirements_text | No | Everything else that matters: cooling, redundancy, certifications, term length, growth plan, budget notes. | |
| additional_services | No | Remote hands, managed services, migration help, etc. | |
| power_per_cabinet_kw | No | Target power density per cabinet, in kW. | |
| expected_contract_date | No | Expected contract signature date, ISO YYYY-MM-DD. | |
| requested_delivery_date | No | Target ready-for-service date, ISO YYYY-MM-DD. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare write operation and idempotency, but the description adds crucial behavior: the confirmation email requirement, asynchronous process (2-3 business days), status_token usage, and broker network coordination. No contradictions with 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 long but every sentence adds critical operational guidance, etiquette, or requirements. It's front-loaded with purpose and flows logically into process, constraints, and follow-up. Slightly dense but earns its length.
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 complex tool with 20 parameters and no output schema, the description covers the full workflow: what happens on submission, confirmation step, expected timeline, status_token handling, and required inputs. Nothing essential for correct invocation 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 covers 90% of parameters, but the description adds value by highlighting required parameters (location, contact.email, agent.on_behalf_of_confirmed) and clarifying the power_kw/power_mw alternative. It doesn't repeat the full schema but supplements it with usage-critical details.
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 states the action (submit), the resource (data center colocation/space requirement), and the target (OCOLO). It distinguishes itself from sibling tools by being the only one that creates a request, while get_broker_guidance and get_project_request_status are for retrieval.
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?
Provides explicit when-to-use context ('quickest way to put a requirement in front of many providers'), broker etiquette, and prohibitions (do not contact providers individually, do not submit to many brokers). It also specifies required fields and the condition for on_behalf_of_confirmed, and points to the sibling for status checking.
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_broker_guidanceget_project_request_statussubmit_project_requestLive power, energy, grid, gas, fiber + off-market data-center capacity in kW/MW — query and cite.
Data Room Picker: the site's own MCP server — compare, enquiry (enquiry = a human handoff, not a...
Live VPS, bare metal and GPU hosting prices across ~75 providers, rescraped daily.
Cold Room Installation Cost: the site's own MCP server — enquiry (enquiry = a human handoff, not...
Add one secure layer between your agents and this server.
