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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful context about content (company-wide vs single-scan scope, hard-coded key detection), but says nothing about pagination, result caps beyond the schema, or freshness of the data.

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 compact sentences with high information density; the field enumeration is front-loaded and the scoping note closes it. It is efficient, though the opening noun phrase is slightly less direct than a verb-first statement would be.

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?

With no output schema, the description carries the burden of describing return values and does so by listing the discovery fields, which is genuinely useful. It is nearly complete for a read-only retrieval tool, with the only real gap being the relationship to discover_shadow_ai.

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 100%, so limit, scan_id, and risk_level are fully documented in the schema, making 3 the baseline. The description only reinforces scan_id's scoping role and adds no syntax or semantic detail beyond what the schema already provides.

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 description states the resource clearly — 'AI usage found in your code and network traffic' — and enumerates the concrete fields returned (provider, model, endpoint, risk level, hard-coded key). It implies a retrieval tool, but never states the verb and does not explicitly distinguish itself from the sibling discover_shadow_ai, which a reader could easily 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?

The trailing clause 'Company-wide, or one scan with scan_id' gives some scoping guidance and implies when to pass a scan_id. However, it never states when to use this tool versus discover_shadow_ai (discovery vs retrieval), which is the key ambiguity given the sibling list.

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