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

The description reveals many non-obvious behaviors: the tool refuses without confirm:true, starts a recurring refresh, returns held_run projections if spend crosses a threshold, and still promotes the table in that case. This goes far beyond the annotations.

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?

The description is dense but every sentence earns its place: main effect, example, consent requirement, precheck, return shape, and edge-case follow-up. It is well organized and front-loads the essential nature of the tool.

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 mutating promotion tool with no output schema, this description covers scenario, human approval, prerequisite check, return values, side effects, and follow-up actions. The only minor gap is cadence parameter details, but overall it is exceptionally complete.

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?

With 0% schema description coverage, the description compensates well for confirm and table_id, including an example and the rule that confirm must be true. Cadence is only indirectly connected to the recurring refresh and return field, so its semantics are slightly underspecified.

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 states the specific action: promoting a table's newest passing version to the version everyone reads. It clearly identifies this as the one human gate, making it easy to distinguish from sibling tools like start_run, confirm_run, and cancel_run.

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 explicitly says to call only when the person the agent is working for has approved it, to check data with query_run first, and to not call start_run for this promotion. It also explains when to follow up with confirm_run or cancel_run.

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