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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds genuinely useful operational context beyond that: it is free, requires no authentication, and is rate limited, which an agent needs for retry/batching decisions.

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?

Four short, front-loaded statements with no filler: purpose/algorithm first, then thresholds, then the inference constraint, then cost/auth. Every sentence carries distinct information.

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?

An output schema exists, so return formatting need not be described. Scoring semantics, thresholds, the no-inference constraint, and cost/auth/rate-limit facts are all present. Only batch-size and field-level handling of the risks payload are unaddressed, a minor gap for a one-parameter tool.

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%, so the schema alone does not explain the 1–5 likelihood/impact scale or its meaning. The description supplies the scale semantics and the threshold bands, partially compensating. However, it says nothing about the risks array shape, the optional mitigation field, or the 100-item limit, leaving the single parameter's structure unexplained.

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?

States a specific verb (Score) and resource (user-supplied risks) plus the exact algorithm (likelihood × impact on a 1–5 scale). No sibling tool does anything similar, so it is unambiguously identifiable.

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 clause 'Does not infer likelihood or impact' is an effective boundary condition: it tells the agent the caller must supply both values rather than expecting the tool to derive them. It stops short of naming alternatives or explicit when-not-to-use conditions, but no sibling competes for this task.

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