Vendor-neutral catalog of 300+ commercial robots: search, compare specs, request vendor intros.
Scored across 5 tools
Each tool targets a clearly distinct operation: free-text discovery (search_robots), single-record retrieval (get_robot), browsing (list_categories), pairwise comparison (compare_robots), and a write action (request_vendor_intros). The search vs. get vs. compare split is explicit about input shape (query/filters vs. slug vs. two slugs), leaving little room for misselection.
All five names follow a strict verb_noun snake_case pattern (compare_robots, get_robot, list_categories, request_vendor_intros, search_robots). Pluralization is sensible (singular for get_robot, plural for collections) and the vocabulary is predictable.
Five tools is well-matched to a read-oriented catalog with one sourcing action; discovery, detail, browsing, comparison, and outreach each map to one tool with no redundancy. Nothing feels padded or conspicuously absent for the stated scope.
The core lifecycle (browse, search, inspect, compare, request intro) is covered, and the compare/get tools handle the catalog's main data needs. However, there are no manufacturer- or category-level detail endpoints (e.g., list/fetch manufacturer profiles) and no pagination or full-listing operation, so agents may hit dead ends when working from a manufacturer name.
Side-by-side spec comparison of two robots by slug, plus RoboHub's editorial verdict when available.
| Name | Required | Description | Default |
|---|---|---|---|
| slug_a | Yes | First robot slug. | |
| slug_b | Yes | Second robot slug. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist; description implies read-only behavior by stating comparison. However, does not explicitly disclose non-destructive nature or any constraints like rate limits or permissions.
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?
Single, concise sentence with no wasted words. Front-loads the core action and includes a relevant extra detail.
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 tool with two parameters and no output schema, description covers basic purpose but lacks detail on return format or what 'specs' means. Adequate but could be more complete.
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 already fully describes parameters (slug_a, slug_b) with 'First/Second robot slug.' Description adds 'by slug' which is consistent but does not enhance meaning beyond 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?
Description clearly states verb 'compare', resource 'two robots', method 'by slug', and additional output 'editorial verdict'. Distinguishes from sibling tools that handle single robots or search.
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?
Implies use for comparing two known robots by slug, but no explicit when-to-use or alternatives listed. Sibling names are provided but not referenced.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full catalog record for one robot by slug: description, specs, SDKs, use cases, verified manufacturer list prices (MSRP) where published, with their date and source; other robots are quote-only or have no public price (see price_provenance) and links.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Robot slug as returned by search_robots (e.g. 'unitree-g1'). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden, and it does meaningful work: it discloses the exact record contents and the non-obvious behavioral trait that only some robots have published MSRP while others are quote-only or have no public price, pointing to price_provenance. It omits auth requirements and error behavior for an invalid slug, keeping it out of 5 territory.
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 dense sentence that front-loads the core purpose ('Full catalog record for one robot by slug') before the field list and the pricing caveat. Every clause carries information, though the semicolon-heavy enumeration of return fields makes it slightly hard to scan.
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 and no annotations, the description must explain what comes back, and it does so thoroughly, including the edge case of missing prices and the pointer to price_provenance. Missing only error/not-found behavior and auth context.
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 exists and schema description coverage is 100%, so the baseline is 3. The phrase 'by slug' adds no meaning beyond the schema, which already defines slug format and its origin from search_robots.
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 (get) and resource (one robot by slug) and enumerates the record contents (description, specs, SDKs, use cases, MSRP, links), which lets an agent separate it from the list-oriented search_robots. It does not name a sibling explicitly, so it falls just short of the top score.
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 only implied: fetching one robot by slug presupposes a prior slug lookup, and the schema (not the description) mentions 'as returned by search_robots'. There is no explicit statement of when to prefer this over compare_robots or search_robots, and no prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
All robot categories with counts and a few example robots each. Good first call to understand catalog coverage.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description mentions it returns counts and examples, but does not disclose read-only nature, auth requirements, or side effects. As a listing tool, behavior is likely safe, but transparency is minimal.
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, direct and to the point. Every word adds value with no redundancy.
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?
Description covers purpose and typical use case. No output schema exists, so the description should hint at return format; it does so with 'counts and a few example robots.' Lacks detail on structure but sufficient for a simple list 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?
Tool has no parameters, so schema coverage is 100%. Description adds context about what is returned (counts, examples), which is sufficient for this zero-parameter tool.
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?
Description clearly states the tool lists all robot categories with counts and example robots. Differentiates from sibling tools like compare_robots and get_robot by focusing on catalog overview.
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?
Describes as a 'good first call to understand catalog coverage,' implying its role as an initial exploratory tool. Lacks explicit when-not-to-use or alternatives, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Record a B2B sourcing request with RoboHub on behalf of the user, for manual review by RoboHub's team. Vendor-neutral and free for buyers. Requests from this server are unverified, so RoboHub sends the buyer no confirmation email and guarantees no reply window. Only call this with the user's explicit consent and their real contact details; submissions are rate limited per client and fabricated requests are discarded.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Work email address where the shortlist should be sent. | ||
| notes | No | Anything else relevant (optional). | |
| company | Yes | Company name. | |
| country | No | Country of deployment (optional). | |
| industry | Yes | Closest industry bucket for the deployment. | |
| timeline | Yes | Deployment timeline. | |
| use_case | Yes | What the robots should do, with as much operational detail as possible (environment, scale, constraints). | |
| robot_slug | No | Slug of a specific robot the user is interested in (optional). | |
| budget_range | Yes | Approximate budget bracket in USD. | |
| contact_name | Yes | Full name of the contact person. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does so thoroughly: it discloses that requests are unverified, no confirmation email is sent, no reply window is guaranteed, submissions are rate limited, and fabricated requests are discarded. This is unusually candid and helps the agent set accurate expectations.
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 three dense sentences with no filler. It front-loads the core purpose, then provides the vendor-neutral and free context, then the critical consent and behavioral caveats.
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 manual-review submission tool with 10 parameters and no annotations, the description covers workflow, caveats, consent, and failure modes well. The only minor gap is that it does not describe what response or confirmation the agent should expect after submission, though the 'no confirmation email' note partially addresses this.
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 schema already documents all parameters. The description adds a real-contact-details and consent requirement, which indirectly relates to email and contact_name, but it does not add new parameter-level meaning beyond what the schema provides.
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 a specific action ('Record a B2B sourcing request... for manual review') and names the target system (RoboHub). It is easily distinguished from the sibling catalog/search tools, which serve a different purpose.
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 clear context for when to call the tool and adds an explicit gate: only call with the user's explicit consent and real contact details. It does not name alternatives, but the sibling tools are robot-information tools, so the intended use is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search RoboHub's catalog of commercial robots by free-text query and optional filters. Returns compact summaries with catalog URLs. When max_price_usd is set: Only robots with a verified manufacturer list price (MSRP) at or below this USD amount; estimates and quote-only robots are excluded.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results to return (default 10, max 25). | |
| query | No | Free-text search over name, manufacturer, category, use cases and description (e.g. 'warehouse pallet AMR', 'quadruped inspection'). | |
| category | No | Restrict to one category. | |
| max_price_usd | No | Only robots with a verified manufacturer list price (MSRP) at or below this USD amount; estimates and quote-only robots are excluded |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden: it does disclose the return format ('compact summaries with catalog URLs') and a meaningful filtering caveat about verified MSRP. However, the MSRP text is duplicated verbatim from the schema, and there is no mention of permissions, rate limits, or pagination behavior.
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?
Front-loaded with the core action in the first sentence, followed by return format and the price constraint. Three tight sentences; the only minor redundancy is restating the max_price_usd rule already in the schema.
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?
No output schema exists, and the description compensates by describing the returned summaries and catalog URLs. For a four-parameter read tool with fully documented params, this is reasonably complete, missing only tie-breaking guidance against siblings.
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 schema already documents all four parameters, establishing a baseline of 3. The description largely repeats the max_price_usd semantics rather than adding syntax or format meaning 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 verb and resource: 'Search RoboHub's catalog of commercial robots by free-text query and optional filters.' This is clear and identifiable, though it does not explicitly name how it differs from siblings like get_robot or list_categories.
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 by 'by free-text query and optional filters' and the price-scoping rule, but there is no explicit when-to-use guidance or routing to alternatives such as get_robot for a specific robot. Adequate but with a clear gap.
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_robots1 field changedInput schema / properties / max_price_usd / descriptionPrevious value: -"Only robots with a known price at or below this USD amount."New value: +"Only robots with a verified manufacturer list price (MSRP) at or below this USD amount; estimates and quote-only robots are excluded"request_vendor_intros2 fields changedInput schema / properties / industry / descriptionPrevious value: -"Industry, e.g. 'logistics', 'agriculture', 'security', 'hospitality'."New value: +"Closest industry bucket for the deployment."Input schema / properties / industry / enumAdded value: +[
+ "manufacturing",
+ "warehouse",
+ "healthcare",
+ "agriculture",
+ "security",
+ "hospitality",
+ "construction",
+ "energy",
+ "research",
+ "other"
+]compare_robotsget_robotlist_categoriesrequest_vendor_introssearch_robotsEvidence-based humanoid robot data: RadarScore ratings, evidence grades A-D, prices, EU availability
Checkout-verified prices, stock, US FCC status and buy routes for humanoid and quadruped robots
Cross-vendor B2B catalog for AI agents: search, compare, find equivalents, request a quote.
Specs of commercially available robots, each figure citing its source document.
Add one secure layer between your agents and this server.
