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

With annotations covering the mutation/safety profile, the description still adds real value: the prompt is only used from the next scheduled check ('nothing runs now'), the plan holds a fixed number of prompts, and a duplicate prompt is not re-added. The trailing line about running 'as the person' is confusing and adds little. Minor tension between 'already tracked is not added again' and idempotentHint=false, but this reads as dedup-with-error rather than a contradiction.

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?

The core action is front-loaded, but the prose is a dense run-on with parenthetical asides, and the closing sentence ('A change inside Kooga: it runs at once, as the person.') is opaque filler that does not earn its place.

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 5-parameter mutation with an output schema and annotations, the description covers timing, plan limits, deduplication, category semantics, and topic discovery. About the only gap is that it doesn't say what happens on a duplicate (error vs silent no-op), which an agent would want to know.

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 80%, so most parameters are already documented. The description's key contribution is explaining the category enum, which the schema leaves as bare values, including the default and the plan-consumption difference between 'topic' and the brand categories. It also reinforces the expected phrasing for 'text'.

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 opening clause names a specific verb+resource ('Add a question to the ones AI Visibility asks the engines on every check') and clarifies the expected phrasing, which is genuinely distinguishable from siblings like addCompetitor or trackKeyword. The category taxonomy further scopes what kind of prompt is being added, though the sentence structure wanders before the point lands.

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 explains when each category applies and which ones consume the plan's brand-prompt allowance ('topic' does not name the brand; 'brand' and 'comparison' count against the plan). It also points to readOptions with kind promptTopics to discover existing topics. It never states when NOT to use this tool versus addCompetitor, but the category guidance covers most selection decisions.

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