Tower evidence

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

Annotations already mark it read-only, so the description's added context is valuable: evidence is untrusted, record IDs should be cited, uncertainty preserved, and human approval is handled separately. It does not describe auth mechanics, pagination, or return shape, but under readOnlyHint that is a moderate 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 filler; the core caveat about untrusted evidence and human approval is front-loaded. Its brevity, however, comes at the cost of missing operational detail, not because of wasteful wording.

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 tool with three parameters and no output schema, the definition omits what evidence is returned, how the parameters shape the result, and when to choose it over sibling tower tools. The safety guidance is useful but does not make the invocation context 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?

Schema description coverage is 0% and the description never mentions limit, source, or agent_id. For three undocumented parameters, the description provides no semantic guidance.

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 names the resource ('Control Tower evidence') but no verb or action, so it does not say whether it retrieves, lists, or queries evidence. It also fails to distinguish this tool from siblings like tower.investigate or tower.incidents.

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 states only that human approval happens via Tower HTTP/CLI separately, which is a boundary note rather than a use case. It gives no when-to-use or when-not-to-use guidance relative to the many other tower.* and lens.* tools.

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