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

Annotations already disclose that this is a non-readonly, non-idempotent, open-world call, so the safety profile is covered. The description adds genuinely non-structured behavior: a decision_id is returned and consumed by handshake tools, and a deny incurs no charge — a billing rule an agent cannot derive from annotations. It still omits auth requirements and whether repeated calls are safe.

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 short sentences with the gating purpose front-loaded, followed by the return contract and the billing rule. No filler, no repetition of the title or schema.

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, so the description need not detail return values beyond the decision_id hint, and annotations cover the mutation profile. Still missing for a billing-relevant decision gate: prerequisites (resolving market/actor identifiers), the consequence of a deny beyond billing, and whether repeat calls create duplicate decisions.

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% with two required, undescribed parameters, so the description carries the full burden. "One market and one actor class" only restates the property names and clarifies cardinality (singular), giving no format, code system, or resolution guidance despite siblings like resolve_jurisdiction and resolve_actor suggesting these values must be resolved first.

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 concrete verb and resource: it issues an allow/deny decision for one market and one actor class, and identifies itself as the pre-handshake gate that emits a decision_id. It stops short of distinguishing itself from the close sibling check_eligibility, which an agent would plausibly confuse with a gating decision.

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?

"The gate before a handshake" implies the correct ordering (call this before handshake tools), which is real sequencing guidance. However there is no explicit when-not guidance and no mention of check_eligibility or a2a_handoff as alternatives, so the agent must infer which sibling owns an eligibility question.

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