Record human decision

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

Annotations only indicate non-readonly non-destructive flags. The description adds a behavioral effect ('Releases the units the decision gated') and a refusal condition, both of which go beyond the structured annotations. No contradiction exists.

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 sentences, with the primary purpose front-loaded and constraints/effects packed tightly afterward. Every clause adds information and there is no repetition or filler.

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 an output schema available, return values need no explanation. The description covers the essential call conditions, refusal context, and side effect, making it complete enough for correct invocation.

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 67%, so the schema already defines most parameters. The description clarifies the choice-vs-withdraw relationship ('or withdraw') which adds meaning beyond the individual parameter descriptions, but it does not otherwise deepen the parameter semantics.

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 specific action ('Record') on a specific resource ('a decision made by a human') and immediately distinguishes the alternative use case ('withdraw a question'). It clearly separates this from sibling tools like request_decision (which asks) and get_decisions (which reads).

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 description gives a decisive usage rule ('Only call with the human's explicit answer') and a hard precondition ('Refused while an OUTSIDE_MODE run is active'). It does not explicitly name when to prefer this over request_decision, but the sibling names and the wording make that inference straightforward.

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