check_answer

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond that: injection-attempt detection, out-of-scope topic flagging, the rule that unverifiable numbers always return REVIEW, empty-answer handling, and the exact return shape. It also discloses a limitation (phrase rules are a baseline only) that an agent needs in order to trust a SEND.

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?

Front-loaded with the one-line purpose, then verification scope, then return shape, then caveats. Dense but every sentence carries information; the description is fairly long and the Args block repeats what the schema already shows, costing a point.

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?

There is no output schema, and the description compensates by spelling out the returned JSON object (decision and flags with type/span/reason/source). Combined with the decision semantics (REVIEW vs SEND) and the precondition skill, an agent has everything needed to invoke and interpret the result.

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 0% and the schema is bare, so the description must carry the load — it documents both params as verbatim customer question and draft answer, and adds the semantic constraint that an empty answer yields REVIEW. It is missing any note on length/format constraints on the raw strings, so it is not a full 5.

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 first sentence names a specific verb (check), a specific resource (an AI-drafted answer to a US retirement-account question) and the workflow position (before it is sent to a customer). It enumerates the verification categories — contribution limits, RMDs, rollovers, early-distribution tax, excess contributions — so an agent can distinguish it from sibling data tools like get_facts and contribution_room.

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?

It gives clear situational context ('before it is sent to a customer') and names a downstream alternative workflow ('also run the advice-judge skill before treating SEND as final'), which is strong routing guidance. It does not explicitly state when not to use this tool versus the siblings (e.g., when you only need raw facts, use get_facts), so it stops short of the 5.

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