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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds real behavioral context: it runs the 'full 40-source screen for each' entity and returns both scores, a verdict, a risk gap, and per-vertical differences. It doesn't discuss latency/cost of a doubled screen, but the disclosure is solid.

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?

Three tight sentences, front-loaded with the definition and followed by mechanics and use case. Minor redundancy between sentence one and the 'which counterparty is riskier' closer, but nothing wasteful.

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 usefully enumerates the return payload (both scores, verdict, gap, per-vertical deltas), which is exactly what an agent needs. Params are fully schema-covered and annotations carry safety. Only the ambiguous entity-matching behavior is left unaddressed.

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 coverage is 100% with both params documented ('First/Second entity name, >=3 chars'). The description only adds that the inputs are 'two entities'; it contributes no extra meaning about names, matching, or resolution behavior, so the baseline 3 applies.

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+resource: 'Side-by-side compliance-risk comparison of two entities.' The comparison framing inherently differentiates it from single-entity siblings like screen_all or sanctions_check, but it never names an alternative explicitly. An agent can still tell what it does without opening the schema.

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?

Usage is implied by 'Answers which counterparty is riskier in one call,' suggesting you reach for it when comparing two entities rather than screening one. There is no explicit when-not guidance and no named alternative (e.g., screen_all for a single entity), so the agent must infer the routing.

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