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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered structurally. The description adds genuinely new context beyond that: what the scan reports (token cost, manifest hash) and a privacy guarantee that nothing sent is stored. It stops short of describing the finding format or output volume.

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?

Three sentences, each earning its place: purpose and scope first, then invocation cadence, then the privacy reassurance. No filler, no repetition of the name or schema, and the most important information is front-loaded.

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 and a single fully-documented parameter, the description carries the remaining burden well: it states what is scanned for, what information accompanies the results, when to call it, and that inputs are not persisted. An agent has everything needed to invoke it correctly.

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?

Only one parameter exists and the schema already documents it at 100% coverage ('Tool definitions as tools/list returned them'). The description's phrase 'loaded in your session' adds session context but no syntax or format detail beyond the schema, so the baseline 3 applies.

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 names a specific verb (scan) and a specific resource (the tool definitions loaded in your session), then enumerates what it looks for: tool poisoning via hidden instructions, concealment, secret access, shadowing, plus quality problems, token cost, and manifest hash. It is far more concrete than a tautology, but it does not explicitly differentiate itself from the many similarly-named siblings (audit_server, verify_tools, check_tool_reliability).

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 explicit invocation timing: 'Call once per session or when a server's tools change.' This is actionable frequency guidance rather than vague context. It does not, however, name an alternative sibling or state when a different tool would be the better choice.

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