recommend_policy

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

With no annotations provided, the description carries the full behavioral burden and does a good job: it discloses a notable side effect — a $0.002 charge paid automatically in USDC — and specifies the decision/return behavior (allow/limit/deny plus recommended policy fields). It does not mention external service dependencies or failure modes, which keeps it from a 5.

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 sentences, roughly 55 words, tightly ordered: core purpose first, return value second, cost last. No filler or repetition; every sentence adds information an agent needs (what it produces, and that invoking it costs money).

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?

The tool is complex (three nested objects, eight nested properties) with no output schema and no annotations, so the description must carry return-value and behavior disclosure. It lists the recommended_policy fields but not their types or structure, and never explains how payment_context.amount influences the decision or whether a prior assessment (e.g., assess_counterparty) is a prerequisite.

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?

Top-level parameter coverage is 0% per the signal, though nested properties (min_confidence, max_payment_usdc, payto_address, etc.) are already well documented in the schema with defaults and examples. The description adds some cross-reference value by labeling max_payment_usdc as a per-counterparty cap and revealing an output-only field (daily_cap_usdc), but it does not explain how the policy, target, or payment_context objects feed the recommendation.

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 states a clear purpose: converting counterparty risk into an enforceable spending policy for an agent wallet, and it enumerates the exact output fields (max_payment_usdc, daily_cap_usdc, add_to_denylist, require_human_approval). The verb is slightly figurative ('Turn...into'), and while the intent is clearly distinct from assessment siblings like assess_counterparty, it never explicitly names what it is not.

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 context is implied rather than stated: the tool is for when you want to apply counterparty risk as a spending policy to an agent wallet. There is no explicit when-to-use vs. when-not-to-use guidance, and no alternatives are named despite close siblings like assess_counterparty and firewall that could also produce risk-based decisions.

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