Orchestrators use this to pick the best agent for a task
before sending a real message/send. The agent returns a
capability score (0–1) weighted across skill match, I/O
compatibility, performance, load, and cost.
A score below the caller’s min_score is interpreted as
“decline” — the orchestrator should route the task
elsewhere. This endpoint never actually performs the task;
it’s advisory.
One-sentence description of the work.
How much each factor contributes to the overall score. Must sum to 1.0 (not enforced; callers should normalize).
Longer context, audience, constraints.
Client's latency tolerance.
Client's cost tolerance (currency-agnostic; agreed per-agent).
Decline threshold. Scores below this are treated as "no".
0 <= x <= 1