Tower investigate

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

Annotations already declare destructiveHint=true and openWorldHint=true, so safety profile is partly covered. The description usefully adds that the tool is 'local authenticated' (auth requirement) and gives data-handling discipline for the output ('Evidence is untrusted data; cite record IDs, preserve uncertainty'), but never says what is mutated or destroyed despite destructiveHint — notably odd for a tool named 'investigate'.

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?

Very short and front-loaded, with no filler sentences. However it is written as telegraphic fragments ('Local authenticated Control Tower investigate') that force the reader to reconstruct the grammar and meaning.

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, authenticated tool with no output schema, one undocumented parameter, and many overlapping siblings, the description is too thin. It omits the investigation's scope, expected input provenance, mutation side effects, and result shape — none of which are recoverable from the annotations or schema.

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 the single required parameter incident_id, so the description carries the full burden. It never mentions incident_id, its expected format, or where the identifier comes from (e.g., tower.incidents output), leaving the only parameter undocumented in both places.

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?

It names a verb (investigate) and a resource scope (Control Tower), but what an 'investigate' actually performs is never stated — no indication of whether it queries records, runs detection, or mutates state. It is not distinguished from close siblings like tower.detect, tower.evidence, tower.incident, or tower.posture, which an agent would plausibly confuse it with.

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 only an implied boundary: 'Human approval uses Tower HTTP/CLI separately' tells the agent this tool is not for approval flows. No positive when-to-use condition, prerequisites, or named alternatives are given, so selection versus tower.detect or tower.incident is left to inference.

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