Tower detect

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

Annotations (destructiveHint=true, openWorldHint=true, readOnlyHint=false) declare the risk profile, and the description adds useful context that evidence is untrusted data to be cited with preserved uncertainty, plus that human approval is a separate path. It stops short of explaining what is destroyed, what authentication is required, or what happens on invocation.

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 sentences with no padding; the scoping (local) and safety notes come first. Efficient, though terseness contributes to the underspecification elsewhere.

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 tool with no output schema and fully undocumented parameters, the description leaves major gaps: what detection means, what is mutated/destroyed, required auth, and result shape. The safety-oriented sentences help but do not fill the void.

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?

Both parameters are undocumented at 0% schema coverage, and the description supplies no meaning for agent_id or evidence_id beyond a passing reference to citing record IDs. With two required params, the description should compensate but does not.

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?

"Local authenticated Control Tower detect" largely restates the name/title; the tool's actual verb and outcome are never stated. An agent cannot tell what "detect" detects or what it produces, and nothing distinguishes it from siblings like tower.investigate or tower.posture.

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?

"Human approval uses Tower HTTP/CLI separately" hints at a division of labor but never states when to call this tool versus tower.investigate, tower.preview, or tower.execute. No explicit when/when-not conditions or prerequisites are given.

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