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

Annotations declare readOnlyHint=true and openWorldHint=false, so the safety profile is already covered. The description adds genuinely non-obvious behavior beyond the annotations: the call is metered and billed via x402 when payments are enabled, and the response includes not just a grade but the missing items and the requirements of the 'quantum realm'. It does not describe caching, latency, or what happens when an agent has no record.

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 grade and scale are front-loaded in the first clause, followed by the scoring components and then the billing note. It is dense and jargon-heavy ('quantum realm', 'Privi'), and the factor list is a single long clause, but every element either defines the score or sets pricing expectations, so little is wasted.

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 explaining the return value, and it does so by naming the scale and the contributing factors. For a single-parameter read tool with annotations covering safety, that is close to sufficient; only the exact response shape and the behavior for unknown or unenrolled agents remain unstated.

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?

There is one parameter, agent_id, and the schema already documents it at full coverage ('A Quantum Agent id'). The description adds no further semantics about identifier format, whether the agent must be enrolled, or whether self-grading is permitted, so it neither compensates nor detracts — the schema does the work.

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 and its output explicitly: an agent's Privi trust grade on an A+ to F, 0-100 scale, computed from named factors (quantum level, passkey approval, ID verification, certificate, key strength, record, minus revocation/impersonation penalties). That is far more informative than the name alone, though it reads more as an output description than a verb+resource statement and never distinguishes itself from near-name siblings such as inspector_check, inspector_status, or inspector_report.

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?

Usage is implied: call this when you want a graded trust assessment plus a gap report ('shows what is missing'). It adds a real operational cue — paid per call via x402 when payments are on, pointing to quantum_pricing — but gives no guidance on when to prefer this over inspector_check, inspector_status, or inspector_report, nor any prerequisites such as whether the agent must be enrolled first.

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