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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, and the description reinforces this usefully by calling the output 'deterministic' and emphasizing it is advisory and non-custodial ('without uncollateralized lending or float'). However, it does not disclose how the optional history inputs (first_seen_days, settled_calls_90d, sponsor_attestations) are treated when omitted — whether they are fetched on-chain or defaulted — which is exactly what an agent needs to know given the openWorldHint.

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, zero waste, with the core capability stated first and the output shape second. The vocabulary is unusually heavy ('non-custodial unsettled exposure advisory evaluation'), which costs some immediate readability, but nothing is redundant.

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 and seven parameters are fully documented, so return values and inputs are covered elsewhere. The remaining gap is the one thing only the description could resolve: whether the caller must supply historical metrics or the tool derives them, given the openWorld annotation and the mostly-optional parameter set with only 'subject' required.

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 100%, so every parameter is already documented in the input schema and the baseline of 3 applies. The description adds nothing at the parameter level; its detail is entirely about output semantics (grade scale, exposure cap), not about how to populate subject, role, or the optional history fields.

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 names the action and resource concretely: it produces a deterministic trust score for a counterparty agent and returns grade (T0-T3), historical success rate, and a suggested maximum settlement exposure. It clearly is not a generic screening tool like sanctions_address_screen or token_contract_risk, though it never explicitly contrasts itself with those siblings. The dense jargon ('unsettled exposure advisory evaluation') slightly obscures an otherwise distinguishable purpose.

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 rather than stated: 'maximum suggested settlement exposure without uncollateralized lending or float' signals the pre-settlement due-diligence context, but there is no explicit when-to-use, when-not, or named alternative among the many screening siblings. An agent must infer that this is the tool to call before extending credit/settlement exposure to an agent address.

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