Setup Approvals

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

Annotations already declare this is a non-read-only, non-destructive, idempotent mutation. The description adds context the annotations cannot: that only one value is accepted, that 'off' is rejected, and that disabling requires a human action elsewhere. It stops short of describing persistence or side effects of the change.

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, front-loaded lines: the action, the when/refusal, and the return shape. No filler sentences.

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?

Given an output schema exists, the 'Returns: {ok, approvals}' line is technically redundant, but the description otherwise covers everything an agent needs: the accepted value, the refusal behavior, and the escape hatch. Complete and unambiguous.

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 100% and the single parameter is fully documented, including the 'off' restriction. The description restates essentially the same constraint, so it adds little meaning beyond the schema.

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?

Names a specific verb (set) and resource (human approvals for live writes) plus the target mode (required). It references the setup_credentials page, giving the agent a way to separate this tool from its closest sibling.

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?

Explicitly states when to use it ('Use when: re-enabling approvals'), states what is refused ('off' is refused here), and routes the agent to the alternative path for turning approvals off (the human on the setup_credentials page). This is precisely the when-to-use / when-not-to-use guidance the dimension asks for.

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