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

Annotations already declare readOnlyHint=false, openWorldHint=true, and destructiveHint=false, so the agent knows this is a non-destructive but stateful, externally-reaching operation. The description adds the '(async)' flag, which is valuable since it implies the call returns before completion and results must be fetched later. However, it omits how/when results become available, expected duration, and any auth or connectivity requirements for the network-traffic scan.

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?

A single front-loaded sentence with a dense but relevant enumeration of scan targets, and no filler. The trailing '(async)' is the only slightly under-explained element, but overall it is efficient.

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 an async discovery scan with no output schema, the description should ideally say how to obtain results and roughly what to expect. It flags async execution but leaves the agent without a retrieval path or expectations for a potentially long-running network scan, so it is only partially complete.

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?

With a single parameter at 100% schema description coverage, the schema already explains that scan_id identifies the uploaded code or repository. The description's phrase 'connected repositories' adds only marginal context, implying the scan_id must reference an already-onboarded target. Baseline 3 is appropriate when the schema does the heavy lifting.

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 (scan) and precise resources (connected repositories, network traffic) plus the exact targets (unmanaged LLMs, model endpoints, vector DBs, agent frameworks, leaked API keys). This makes it clearly distinguishable from siblings like code_review_scan or compliance_scan. It does not explicitly name a sibling to contrast against, so it falls short of a 5.

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 no when-to-use guidance, no prerequisites, and no mention of alternatives among the many scan-type siblings (code_review_scan, compliance_scan, generate_threat_model). The '(async)' note hints at invocation behavior but gives no routing guidance. An agent must infer that this is the tool for shadow-AI discovery purely from the resource list.

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