Read-only catalogue search: JVM tooling, ML models, compliance APIs, siSwati LLM, Veridix markets.
Scored across 4 tools
Each tool has a distinct role: contact info, single-product lookup, full capability listing, and free-text search. list_capabilities and search_products both answer 'what do they do', so there is mild overlap, but the descriptions clearly steer broad open questions to one and keyword queries to the other.
All four tools follow a clean verb_noun snake_case pattern (get_contact_info, get_product, list_capabilities, search_products). No mixed conventions or vague verbs.
Four tools is on the lean side but well matched to a read-only public catalogue: search, retrieve by slug, browse all, and a contact route. Each earns its place with no redundancy.
For a read-only catalogue the surface is nearly complete: free-text discovery, full listing, single-item detail, and a contact channel. There is no pagination/browse-by-category operation, but agents can work around that via search and list_capabilities.
How to get in touch, and which route suits which enquiry — partnerships, white-labelling the APIs, research collaboration, or access to the Veridix platform. Read-only: this reports the routes, it does not send anything.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description explicitly discloses the read-only, non-sending behavior ('it reports the routes, it does not send anything'), which adds behavioral context beyond the annotations. This reassures the agent that using the tool has no side effects, complementing the readOnlyHint and idempotentHint 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 concise yet informative, front-loading the core purpose and then adding the read-only clarification. Every sentence earns its place—the first defines what it does, the second enumerates the enquiry types, and the third clarifies behavioral safety.
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 zero parameters, the presence of an output schema, and comprehensive annotations, the description is complete. It explains the purpose, the routing categories, and the non-sending behavior, leaving no obvious gaps for an agent to invoke 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?
The tool has zero parameters, and the schema coverage is trivially 100%. The description doesn't need to explain parameter semantics since there are none; the baseline of 4 is appropriate because there is nothing to compensate for.
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 tool's function: getting in touch with Netbrain and identifying which contact route suits various enquiry types. It explicitly lists the categories of enquiries (partnerships, white-labelling, research collaboration, platform access), which distinguishes it from sibling tools about products and capabilities.
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 clear context on when to use this tool—whenever an agent or user needs contact information or routing for specific enquiry types. It doesn't explicitly name alternatives or exclusion conditions, but given the sibling tools are product/capability-focused, the usage context is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full detail for a single Netbrain product or platform, by slug. Use search_products first if you do not already know the slug.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | The catalogue slug, e.g. "siswati-llm". |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety and idempotency profile is fully covered by structured fields. The description adds only the slug-discovery workflow hint, and says nothing about return shape or lookup failure behavior beyond what the output schema and annotations provide.
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 waste, with the core purpose front-loaded and the routing hint second. Nothing could be trimmed without losing guidance.
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 one-parameter, read-only lookup with an output schema and full annotation coverage, the description supplies everything an agent needs: what it returns, how to invoke it, and how to obtain the required slug. No meaningful gap remains.
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 100% and the single slug parameter is fully documented with an enum and example in the schema. The description mentions 'by slug' but adds no format, casing, or fallback semantics beyond what the schema already states, 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: 'Full detail for a single Netbrain product or platform, by slug.' The word 'single' plus 'by slug' scopes it precisely and implicitly separates it from the sibling search_products.
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 names the alternative and the condition selecting it: 'Use search_products first if you do not already know the slug.' This is exactly the when/when-not guidance needed, with no inference required.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Everything Netbrain builds, grouped by category, with the capabilities and technologies under each. Use this for open questions like "what does Netbrain do" or "can they help with X" where no single product is obviously the answer.
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Optional. Limit to one category. |
| Name | Required | Description |
|---|---|---|
| categories | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds only that this is a complete inventory grouped by category, and says nothing about size, pagination, or truncation of the full catalog, so it adds limited value beyond the structured fields.
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, zero waste: the first defines the output shape, the second defines when to pick this tool. The routing information is front-loaded and nothing is repeated.
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, so return values need no prose, and annotations carry the safety profile. Purpose, scope, and selection criteria are all covered, leaving no gap an agent needs filled before invoking the 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?
Schema coverage is 100% and the single 'category' parameter already documents its enum values in the schema. The description never mentions the category filter, so it adds no meaning beyond what the schema provides — the baseline 3 for full coverage.
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 concrete resource ('Everything Netbrain builds') and its structure ('grouped by category, with the capabilities and technologies under each'), so an agent knows exactly what is returned. It differentiates from siblings indirectly via 'where no single product is obviously the answer,' which rules out get_product/search_products, but never names them.
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 when-to-use condition ('open questions like "what does Netbrain do" or "can they help with X"') and an implicit when-not ('where no single product is obviously the answer'). However, it never names the alternative tools an agent should route to for product-specific questions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free-text search across every Netbrain product and platform — names, descriptions, capabilities, technologies and tags. Use this to answer questions like "does Netbrain do static analysis for Kotlin", "what can they do for KYC compliance", or "do they have anything for African languages". Returns matching entries with a relevance score, best match first.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | What to search for. Free text: a technology, a problem, a product name, or a capability. | |
| listing | No | Optional. "product" is a developer tool installed from a public marketplace (JetBrains Marketplace, Open VSX); "platform" is run by Netbrain and is live at its own site or arranged by enquiry. | |
| category | No | Optional. Restrict results to one category. |
| Name | Required | Description |
|---|---|---|
| results | Yes | |
| matchCount | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds that results are ranked, best match first, which is useful behavioral context, but says nothing about result limits, pagination, or what a weak/no-match query returns. Adequate but not rich.
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?
Three sentences, front-loaded with verb-plus-resource, followed by illustrative examples and the return shape. No filler and nothing repeated verbatim from the structured fields.
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 a full output schema, complete parameter documentation, and rich annotations, the description only needs to convey search scope and intent, which it does. The example queries are a genuine bonus; only edge behavior (empty results, ranking ties) is left unaddressed.
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%, with both optional enums (listing, category) fully documented in the schema itself. The description adds no query syntax or filtering nuance beyond what the schema provides, 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 (free-text search) and resource (Netbrain products and platforms), and enumerates the searchable fields (names, descriptions, capabilities, technologies, tags). The scope clearly separates it from single-item siblings like get_product or list_capabilities, though no sibling is named explicitly.
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?
Gives concrete example question shapes that show the intended use case (capability-shopping questions like "does Netbrain do static analysis for Kotlin"). It stops short of any when-not guidance or explicit routing to get_product/list_capabilities, so 4 rather than 5.
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_product1 field changedInput schema / properties / slug / enumPrevious value: -[
- "smart-java-kotlin-analyzer",
- "intellij-benchmarking",
- "spring-boot-monitoring",
- "numerai-models",
- "compliance-api",
- "cross-chain-api",
- "siswati-llm",
- "veridix-market-prediction-platform"
-]New value: +[
+ "smart-java-kotlin-analyzer",
+ "bugbench",
+ "spring-boot-monitoring",
+ "compliance-api",
+ "cross-chain-api",
+ "siswati-llm",
+ "veridix-market-prediction-platform"
+]list_capabilities1 field changedInput schema / properties / category / enumPrevious value: -[
- "developer-tooling",
- "applied-ml",
- "platform-api",
- "language-model",
- "platform"
-]New value: +[
+ "developer-tooling",
+ "platform-api",
+ "language-model",
+ "platform"
+]search_products2 fields changedInput schema / properties / category / enumPrevious value: -[
- "developer-tooling",
- "applied-ml",
- "platform-api",
- "language-model",
- "platform"
-]New value: +[
+ "developer-tooling",
+ "platform-api",
+ "language-model",
+ "platform"
+]Input schema / properties / listing / descriptionPrevious value: -"Optional. \"product\" carries a price in the store and is bought there; \"platform\" carries no price, and access is arranged by enquiry instead."New value: +"Optional. \"product\" is a developer tool installed from a public marketplace (JetBrains Marketplace, Open VSX); \"platform\" is run by Netbrain and is live at its own site or arranged by enquiry."get_contact_infoget_productlist_capabilitiessearch_productsSearch a curated directory of agent tools, MCP servers, APIs, protocols and skills. No auth.
Query the HokAI catalogue of AI tools, agents, models, companies and infrastructure services.
Search and read the aicoolies catalog of AI and developer tools via a remote MCP knowledge graph.
Find governed AI capabilities and verify signed receipts. Read-only, no account.
Add one secure layer between your agents and this server.
