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

Adds real context beyond the annotations: the call is asynchronous ('returns immediately'), the target set is fixed by the console, and results must be fetched with other tools. One tension worth noting is the phrase 'read-only scan' alongside readOnlyHint=false — accurate in the sense that the customer clouds are not modified, but an agent must not read it as 'no server-side side effects', since this triggers a job; the annotation remains the authoritative signal and the description does not overtly claim the tool is a pure read.

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?

Two sentences, both front-loaded and load-bearing: the first defines the action and its scope constraint, the second defines the async contract and the next step. Nothing is repeated from the title or annotations.

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 zero-parameter, no-output-schema trigger tool this covers what an agent needs: what it does, that it returns immediately, and where the results surface. Only minor gaps remain, such as whether repeat invocations are cheap or whether a scan is already in flight.

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 there is nothing for the description to disambiguate; the baseline applies. The description does usefully establish that the agent cannot pass cloud/account identifiers to narrow the scan, which is the one parameter-related misconception this tool invites.

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 ('Start a fresh ... scan') and a precisely bounded resource ('the clouds already connected to this workspace'), and rules out an adjacent reading by clarifying that cloud connections are made in the Redthread console, never through this tool. That scope makes it trivially distinguishable from siblings like list_cloud_findings or get_security_overview.

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?

Tells the agent when to reach for it (to refresh/re-scan existing connections) and explicitly routes follow-up work to get_security_overview or list_attack_paths, which prevents the common mistake of expecting results in the return value. It stops short of stating exclusions or cost/rate considerations (e.g., how often a re-scan is sensible), so it is strong but not complete.

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