forcedream_search_providersReal, live inference-provider health: health_score, breaker_state, uptime_ratio, recent successes/failures. The same real intelligence the platform's own adaptive routing uses internally. No key needed.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| providers | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds value by specifying the live, real-time nature, the exact metrics returned, and that no authentication key is required. No contradiction with 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?
Two sentences, front-loaded with key terms and no filler. Every sentence adds distinct value.
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 parameters and an output schema present (though unseen), the description fully covers the tool's purpose and data. No gaps.
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?
Input schema has zero parameters (100% coverage by default), so description does not need to explain parameters. Baseline 4 is appropriate.
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 it provides 'Real, live inference-provider health' with specific metrics (health_score, breaker_state, uptime_ratio, successes/failures), and distinguishes itself from siblings by noting it mirrors the platform's internal adaptive routing data.
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?
States 'No key needed' implying open access, but does not explicitly specify when to use this tool vs. siblings like forcedream_search_reliability or forcedream_search_costs. Usage guidance is implied but not contrasted.
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.
Most tools have clearly distinct purposes (fraud vs extract vs generate vs sentiment vs lead scoring vs quote vs proof verification). However, there is notable overlap among the search_* discovery tools: forcedream_search_agents, forcedream_search_reliability, and forcedream_search_costs all surface overlapping agent metadata (success_rate appears in both search_agents and search_reliability), which could cause misselection. Additionally, forcedream_extract_data vs forcedream_extract_entities vs forcedream_extract_action_items overlap somewhat in the extraction domain despite distinct outputs (JSON fields vs raw entities vs action items).
The forcedream_ prefix is used consistently throughout, and most tools follow a forcedream_<verb>_<object> pattern (extract_data, generate_code, score_lead, security_scan). However, there is inconsistency in verb style: check vs extract vs generate vs invoke vs search vs verify vs summarize are all different verb types, and the objects don't follow a uniform noun convention (some are actions like invole_agent, others resources like market_quote). The naming is readable and discoverable but not perfectly uniform.
At 17 tools, this is slightly above the ideal range but justifiable given the broad multi-service scope (fraud, extraction, generation, discovery, verification). Each tool maps to a reasonably distinct service capability, and none feel like padding. The count borders on heavy but earns its place given the diverse domain coverage.
The tool surface is comprehensive for a multi-purpose AI/ML service platform, covering fraud detection, data extraction, code generation, sentiment analysis, embeddings, lead scoring, security scanning, summarization, market quotes, agent discovery, and proof verification. Missing are update/delete operations, but this appears to be a stateless service rather than a CRUD resource store. The discovery tools (search_* variants) and meta capabilities (verify_proof) round out the lifecycle well, though there's no clear cleanup or batch-processing tool.