AgentBroker is a remote MCP server for discovering and inspecting a canonical catalog of API and agent services. It exposes structured service metadata, input/output schemas, provider information, and current pricing through MCP tools such as search_services and get_service.
Scored across 2 tools
The two tools have clearly distinct purposes: get_service retrieves full details for a single service by ID, while search_services performs a catalog-wide search. There is no overlap in functionality and the names and descriptions make the distinction obvious.
Both tools follow a consistent verb_noun pattern (get_service, search_services). The naming convention is predictable and readable.
Only 2 tools is somewhat thin for a service catalog broker. While it may cover the minimal read operations, typical broker functionality (e.g., subscribing, purchasing, or listing) is absent, making the count feel borderline too few.
The surface covers retrieval and search, which are core read operations. However, there are no tools for write actions like creating or updating services, or for user interactions such as purchasing or subscribing, leaving notable gaps for an agent broker.
Get full metadata, input schema, output schema and current retail price for one canonical AgentBroker service.
| Name | Required | Description | Default |
|---|---|---|---|
| canonical_service_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It does disclose the payload contents (metadata, schemas, price), which is useful, but says nothing about authorization, error behavior for invalid canonical ids, or whether results are cached/live.
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?
One front-loaded sentence with a clear verb and an explicit enumeration of the returned artifacts. No filler or 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?
With no output schema present, the description usefully enumerates the returned fields, which is the key completeness requirement here. The remaining gap is failure/error behavior and where a canonical id comes from, but for a one-parameter read tool the coverage is close to 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?
Schema description coverage is 0% and the description only repeats the notion already encoded in the parameter name (canonical_service_id, i.e. a canonical service). It adds no format, example, or source for obtaining a valid id, so it does not compensate for the coverage gap.
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 canonical AgentBroker service), and enumerates what is retrieved (metadata, input/output schemas, retail price). It implies the single-item counterpart to search_services, but never names that sibling, so the differentiation is inferable rather than explicit.
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 phrase 'for one canonical AgentBroker service' implicitly tells the agent this is a single-record lookup versus the many-record search_services, but there is no explicit when-to-use guidance, no prerequisites, and no statement about what happens if the id is unknown.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the AgentBroker service catalog. Returns matching active services with canonical ID, supplier-backed retail price and summary.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | Keyword search |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral burden. It usefully discloses that only active services are returned and names the returned fields, but says nothing about result ordering, pagination, rate limits, or empty-result 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?
Two sentences, zero filler, and the purpose is front-loaded with the return shape following immediately. Nothing is repeated 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 no output schema, the description reasonably compensates by describing the return fields. However, it leaves the limit parameter undefined and gives no basis for choosing this tool over get_service, so the definition is adequate but incomplete.
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 only 50% — 'query' has a description but 'limit' (default 20, max 50) is undocumented in both schema and description. The description implies keyword matching returns matches, but adds no syntax or scope guidance for query and ignores limit entirely.
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 (Search) and resource (AgentBroker service catalog) and even previews the return shape (active services with canonical ID, price, summary). It does not explicitly differentiate itself from the sibling get_service, but the search-vs-fetch distinction is strongly implied.
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?
No statement of when to use this tool versus get_service, no mention that it is for discovery before fetching a specific service, and no prerequisites. An agent must infer routing from the names alone.
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_servicesearch_services
