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

Annotations already declare idempotentHint=true and destructiveHint=false, but the description adds genuinely new behavior: this is an owner-level change that triggers a post-hoc notice to the owner, and the reason text is surfaced in that notice. The retry sentence partly restates idempotentHint, and the phrase 'owner-level change' leaves it slightly unclear whether approval is required beforehand.

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?

Four short sentences, front-loaded with the action, then prerequisites, then retry semantics, then side effects. 'as the On switch in Automations > Scanners does' is slightly informal but does real work; the 'Sergio tells the owner' sentence is awkwardly voiced but carries substantive information.

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 4-parameter mutation with no output schema, the description covers id source, idempotency, binary state, and the owner-notification side effect, which is enough to call it correctly. It omits what a success response looks like and whether the change is reversible, which would have closed the remaining gap.

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 coverage is only 50%, and the description compensates for the most important gap by naming the source of scanner_id (read('scanners')) and by clarifying that enabled is strictly binary with no trial mode. It still adds nothing about failure modes for a bad uuid, but the key semantics of the two undocumented-looking params are covered.

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?

States a specific verb and resource (turn a Scanner on/off) and pins the exact counterpart in the UI (the On switch in Automations > Scanners), which makes the effect unambiguous. It also rules out a neighboring state an agent might assume exists ('never a trial mode'), which separates this cleanly from edit_scanner or create_scanner.

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?

Gives concrete usage context: scanner_id must come from read('scanners'), and the same idempotency_key must be reused on retries. It does not explicitly say when to prefer this over edit_scanner or what to do if the Scanner is already in the requested state, so a small inference remains.

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