score

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this read-only and idempotent, and the description adds non-obvious behavior: 'Synchronous deterministic compute; nothing is persisted.' It also discloses the scoring formula and the fact that no state is modified, which fully covers the safety profile.

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 compact and front-loaded: purpose first, then formula and defaults, then routing guidance, then behavior and returns. Every sentence earns its place; it packs a lot of information without 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, the description lists all return fields (recommended_action, expected_value, probability_of_loss, score, score_breakdown). The nested request payload is handled by pointing to simulate's payload shape and POST /v1/score, and side effects are explicitly addressed, so the agent has enough to call it correctly.

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?

Although schema coverage is 100%, the description adds real meaning beyond the schema: scoring_weights is explained as tuning the blend, with exact defaults (expected_value 0.6, downside_risk 0.4) and the formula using normalized expected value and one minus probability of loss. It also clarifies that request uses the same payload shape as simulate.

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 opens with a specific verb-resource pair ('Run one simulation request') and names the exact return fields, so an agent knows what the tool produces. It also positions score against simulate and compare, explicitly saying simulate is for the full envelope without scoring and compare is for ranking scenarios.

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?

It gives direct routing guidance: 'Use simulate when you need the full envelope without scoring, and compare to rank several scenarios.' This tells the agent when score is not the right choice and identifies the alternatives by name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.