Tower runbook_verify

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

Annotations already flag readOnlyHint=false, destructiveHint=true, and openWorldHint=true, so the mutation risk is visible. The description adds genuinely new context — that the call is authenticated and that returned evidence must be treated as untrusted data with record IDs cited and uncertainty preserved. It does not clarify why the operation is destructive or whether prior verification results are replaced, which is the main remaining gap.

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 no bloat, and the data-handling guidance is useful. However, the leading sentence is pure redundancy with the name and title, so the content that actually earns its place is only two sentences long.

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?

This is a destructive, open-world mutation with three undocumented required parameters and no output schema. The description covers the trust posture of returned evidence but omits the core semantics — what verification means, what it consumes, and what state it alters — leaving too much for the agent to infer.

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% and all three required parameters (execution_id, lens_evidence_id, evals_evidence_id) are bare strings. The mention of citing record IDs gives a faint hint that the evidence IDs are record identifiers, but the description never explains the distinct role of each parameter or whether the evidence must come from prior lens/evals runs.

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 opening sentence "Authenticated Control Tower runbook_verify" restates the tool name and title rather than stating what verification does. The parameter names hint that an execution is checked against lens and evals evidence, but the description never says so; an agent cannot distinguish this from tower.verify or lens.execution_verify on the basis of the text.

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 only routing signal is "Human approval uses Tower HTTP/CLI separately," which marks a boundary but does not say when to call this versus tower.runbook_preview, tower.runbook_execute, or tower.verify. No prerequisites, ordering, or exclusions are given.

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