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

Annotations declare readOnlyHint=false and openWorldHint=true, so behavior beyond a read is expected. The 'counts as one Gate call per token' quota/billing detail is useful context not in the annotations, but for a non-read-only operation the description never says what state it creates (receipts), whether it is destructive or idempotent, or what authorization is needed.

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 compact clauses, front-loaded with the batch ceiling and the one-policy constraint. Nothing is padding; the style is terse but every phrase carries 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?

For a non-read-only, no-output-schema tool, the definition never explains what a receipt contains, whether the call is all-or-nothing when one token fails, or how partial errors surface — gaps that matter for a batch mutation. Slightly richer parameter coverage of tokens would also help.

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 50%: policy is richly documented inline (preset name or object with deny_if/unknown/review_if, default actuary-default-v1, pointer to gate_facts) while tokens has only an array type and maxItems. The description reinforces the 10-item cap and the single-policy restriction, adding some meaning for tokens but little for policy.

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 and resource: gate up to 10 tokens against one policy in a single call, with one receipt per token. The batch cap and 'one policy' constraint distinguish it from the single-token sibling gate, though the description never names that alternative explicitly.

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 'up to 10 tokens against one policy in one call' — the agent can infer this is the multi-token path. But there is no explicit when-not guidance (e.g. use gate for a single token, or what to do if tokens need differing policies) and no stated prerequisites.

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