search_capabilitiesWHEN: Use when the user named a setup in trader language and you need to know which Dantes skill matches.
NOT for: Do not use to run a scan or to invent a skill we do not list.
Returns: Matching capability ids, each with its price, what it takes to run it, and its own when / not_for / returns — plus not_encoded, the setups this endpoint does not have.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| category | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the return shape (capability ids with price, run requirements, nested when/not_for/returns) and the notable not_encoded field. It does not mention side effects or pagination, but the read-only nature is implied by the 'NOT for running a scan' guidance.
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 organized into WHEN / NOT for / Returns blocks, each contributing distinct guidance. It is slightly wordy but efficient and front-loaded with the central trigger condition.
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 provides enough context for an agent to decide when to call search_capabilities and what to expect back, including the not_encoded caveat. However, it omits any definition of the category parameter and provides no example, which is a noticeable gap given the sparse schema.
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 does not explicitly define the query or category parameters. It implies query is the trader-language setup mentioned in WHEN, but category is completely undocumented, leaving an optional parameter ambiguous.
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 states a clear action—searching capabilities—and the trigger condition ('user named a setup in trader language'). It distinguishes itself from siblings like get_capability and invoke_capability by focusing on discovery/identification rather than retrieval or execution.
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 WHEN and NOT for sections explicitly state when to use the tool and what not to do ('Do not use to run a scan or to invent a skill'). It does not name sibling alternatives directly, but the exclusion is clear enough to guide tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool serves a clearly distinct purpose: searching for capabilities, fetching details for a known id, listing datasets, invoking a paid scan, and retrieving historical evidence. There is no overlap between discovery, introspection, execution, and evidence retrieval.
All tool names follow a consistent verb_noun snake_case pattern: get_capability, get_capability_evidence, invoke_capability, list_datasets, search_capabilities. The verbs (get, invoke, list, search) clearly reflect the operation type and maintain a uniform style.
Five tools is an appropriate scope for a capability marketplace server. Each tool earns its place covering discovery, metadata, datasets, execution, and evidence without unnecessary redundancy.
The tool surface covers the full workflow: find a capability (search_capabilities), inspect its manifest (get_capability), see available universes (list_datasets), run it (invoke_capability), and retrieve historical evidence (get_capability_evidence). No major gaps are apparent for the server's stated purpose.