Tower incidents

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

readOnlyHint=true already declares the operation is non-mutating, so the description needs to add beyond that. It does contribute real behavioral context: evidence is untrusted data, record IDs must be cited, uncertainty preserved, and approvals are out-of-band — useful handling rules — but it says nothing about scope, freshness, or volume of results.

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 clauses with no filler and the trust/auth caveat front-loaded. The opening is a noun fragment rather than a statement of what is returned, which costs a point on structure but nothing is wasted.

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 zero parameters and no output schema, the description is the agent's only source of truth about what comes back, and it never says whether this returns a list, a count, or full incident bodies. The evidence-handling and approval-boundary notes are good, but the return shape and scope remain undisclosed.

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 takes zero parameters, so per the baseline this dimension defaults to 4; there is no parameter surface the description could clarify further.

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 incidents') but never supplies a verb — it is unclear whether this lists incidents, fetches all incidents, or returns a portfolio summary. The sibling 'tower.incident' (singular) is not referenced, so an agent cannot confidently tell the plural read from the singular drill-down.

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?

No when-to-use guidance is given and no alternative is named, even though 'tower.incident', 'tower.investigate' and 'tower.detect' are obvious siblings for incident scenarios. The only routing hint is the closing note that human approval happens via Tower HTTP/CLI, which tells the agent what this tool does not do rather than when to pick it.

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