Search the HumanMirror Nexus catalog for a machine-callable tool that matches a task. This search is free and does not consume credits.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Describe the operation the agent needs. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It discloses a meaningful trait—that the search is free and consumes no credits—which helps an agent decide to use it early. It does not explicitly state that the search has no side effects or what the result shape is, but 'search' strongly implies a read-only operation.
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 two concise sentences with no filler. The primary behavior is front-loaded, and the credit-related note is a valuable, separate addition that earns its place.
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 single-parameter search tool with no output schema, the description is largely complete: it states what is searched, what is returned conceptually (matching machine-callable tools), and the free nature of the operation. It could be more complete by mentioning how results should be used afterward, but that is not essential for invocation.
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 query parameter is already documented as 'Describe the operation the agent needs.' The description adds only a slight shift in framing by calling the input a 'task,' which is helpful but not essential. This meets the baseline for high schema 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 states a specific verb ('Search') and resource ('HumanMirror Nexus catalog'), and clarifies the purpose is finding a machine-callable tool that matches a task. It is clear and distinct from siblings like nexus_call or outcome_run, though it does not explicitly name or contrast any sibling.
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 implies when to use the tool: when an agent needs to discover which catalog tool fits a task. The added note that the search is free and does not consume credits gives useful selection context, but it does not explicitly state when to use this over alternatives such as nexus_call or outcome_run.
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.
The tools divide cleanly into nexus routing and outcome contract flows, but magnet_resolve and nexus_search both perform free task-to-tool matching, which could cause an agent to pause over which discovery path to use. All other tools have clearly distinct roles.
Every tool follows the same noun_verb snake_case pattern: magnet_resolve, nexus_call, nexus_search, outcome_quote, outcome_run, outcome_verify. The prefix groups reinforce the two subsystems while keeping a single consistent naming convention.
Six tools is well-scoped for a bridge/marketplace server: two for standard Nexus discovery and execution, one fallback discovery mechanism, and three for the Outcome contract lifecycle. Each tool earns its place without redundancy.
The server covers the full agent-facing workflow: discover a tool, execute it, and separately quote, run, and verify success-only Outcome contracts. It also records capability gaps through magnet_resolve, leaving no obvious dead end for the stated purpose.