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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds genuinely new behavior: prepaid pricing of $0.15 per successful call, determinism, and the fail-to-review rule for unknown targets. The 'read-only' wording sits in mild tension with readOnlyHint=false, but the disclosed per-call charge explains the non-read-only annotation and prevents cost surprises.

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 with no filler, leading with cost then purpose then the one edge-case rule. Slightly awkward that price precedes the purpose statement, but nothing is wasted.

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 never says what the verdict looks like or what values it can take (allow/deny/review), which is the key thing an agent needs to act on the result. For a policy-gate tool with a 9-field nested request and no output schema, this is an incomplete picture.

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% across a 9-field request object (only 'target' is annotated), so the description must carry the burden. It adds meaning for amount, destination, and approval ceiling and notes the caller supplies the policy, but says nothing about allowed_targets, blocked_targets, max_spend_usd, or unlimited_approval.

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 a concrete operation and resource: a 'spend policy verdict' over 'amount, destination, and approval ceiling,' which an agent can distinguish from siblings like tx_preflight or allowance_risk_check. It stops short of naming an alternative explicitly, so it is clear but not fully sibling-differentiating.

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?

'Caller supplies policy; unknown targets require review' gives a hint about context and prerequisites, but there is no statement of when to prefer this over allowance_risk_check or tx_preflight, nor any exclusion. Usage is implied rather than directed.

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