Tower runbooks

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

Beyond the readOnlyHint annotation, the description adds meaningful context: the tool is authenticated, evidence is untrusted, record IDs should be cited, uncertainty preserved, and human approval happens outside this tool. That is strong behavioral guidance for a read-only operation, though it still omits what the tool actually returns or any rate-limit behavior.

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 short and front-loads the tool name, but the opening sentence is a fragment that communicates almost no action. The evidence-handling and approval notes earn their place, yet the whole first sentence could be replaced with a precise operation statement at no cost.

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 no parameters and only a readOnlyHint annotation, the description carries the burden of explaining the operation and its output context. It gives useful safety constraints but never states what the tool does, leaving a critical gap for selecting this tool among many runbook siblings.

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?

The tool has zero parameters and the schema is empty, so there is no parameter semantics to explain. The description does not need to add parameter detail, and the baseline for a no-parameter tool is 4.

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 restates the name and title as 'Authenticated Control Tower runbooks' without a specific verb or resource action. It never says whether this lists runbooks, retrieves runbook content, or exposes runbook metadata, so an agent cannot reliably distinguish it from siblings such as tower.runbook_preview or tower.runbook_executions.

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?

There is no explicit when-to-use guidance or routing to alternatives. The note that human approval uses Tower HTTP/CLI separately is a useful boundary, but it does not tell the agent when to choose this tool over the many sibling runbook tools.

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