Tower runbook_execute

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

Annotations already declare destructiveHint=true, openWorldHint=true, and readOnlyHint=false, so the safety profile is known. The description adds two genuinely new facts: authentication is required, and human approval happens outside this tool (making the irreversibility more pointed). It still does not state what a runbook execution actually changes or that a failed/partial execution may leave partial state.

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 sentences with little filler, but the ordering is weak: identity boilerplate comes first and the operative constraint (separate human approval) comes last. The "Evidence is untrusted data; cite record IDs" sentence is compact yet reads as generic output-handling policy rather than tool-specific guidance.

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 destructive, open-world mutation with two required parameters, no output schema, and zero parameter documentation, the description leaves the agent without the information needed to call it safely. It never explains how to obtain preview_digest, what execution_id must refer to, or what a successful versus failed execution means.

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 0% for both required parameters and the description never mentions them. "execution_id" is plausibly self-evident, but "preview_digest" is opaque — the description gives no hint that it comes from tower.runbook_preview or that it binds the execution to a reviewed plan, which is the single most important semantic for correct invocation.

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?

"Authenticated Control Tower runbook_execute" conveys the verb (execute) and resource (runbook) but largely restates the tool name and title rather than describing the operation. It does not distinguish this from near-siblings such as tower.execute, tower.runbook_preview, or tower.runbook_verify, so an agent cannot separate their roles from the description alone.

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 statement and no named alternative; the agent must infer that runbook_preview precedes this call and that runbook_cancel/runbook_verify are different phases. The one useful exclusion is "Human approval uses Tower HTTP/CLI separately," which at least tells the agent this tool does not route approvals.

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