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. The description adds genuinely useful non-schema behavior — it is paid-only, costs 5 prepaid credits, and requires production billing — which materially affects whether an agent can call it. It says nothing about the return shape or what happens when the p95 target is breached.

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 short sentences, with the core computation front-loaded and the billing constraint immediately after. Nothing is redundant and nothing is padded.

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 simple two-parameter computation with no output schema, the description is close to adequate, but it never explains the response (e.g. computed percentiles plus pass/fail) or how a breach is reported. The undocumented parameters and the unexplained paid gate leave real gaps.

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 coverage is 0%, so the description must carry the load, and it does partially: it establishes that samples are millisecond values from which percentiles are derived and that a target is compared against them.

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 and resource ('Compute p50, p95, p99 from supplied milliseconds and compare target'), so an agent knows exactly what computation happens. It does not distinguish itself from the closely named sibling privi_latency_percentiles, leaving some ambiguity about which percentile tool to pick.

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 / when-not-to-use guidance and no mention of alternatives such as privi_latency_percentiles or privi_pro_uptime_slo. The only selection signal is the payment warning, which is about eligibility rather than task fit.

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