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

Annotations already declare readOnly/idempotent/non-destructive, so the lower bar applies, yet the description still adds real substance: the score is weighted, it covers only the checks applicable to this account, and it reports how many checks could actually be evaluated (a key caveat for trusting the number). It does not explain cost, latency, or what happens with a too-short lookback window.

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, front-loaded with the return value and immediately followed by the scope caveat; nothing is padded. Minor density cost from the embedded clause about the audit's 74 checks.

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?

Output schema exists, so return values need no prose, and annotations cover the safety profile. But for a tool with four undocumented parameters (including a lookback window defaulting to 30 days) the description leaves too much for the agent to guess about how to configure the call.

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 0% across four parameters, so the description must compensate and it does not: days, detail, render and customer_id are never mentioned. In particular the summary/full detail enum is ambiguous — it is unclear whether 'full' reintroduces findings, which directly conflicts with the 'no findings' promise.

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?

Names a specific artifact (weighted 0-100 health score with letter grade and per-category breakdown) computed over the audit's applicable checks, and states what it does NOT return (findings, evidence). That scope statement implicitly separates it from full_audit-style siblings, though it never names the alternative tool outright.

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 phrase 'the cheapest way to ask how the account is doing' implies a quick-glance use case versus deeper audit tools, but there is no explicit 'use this when X, use full_audit when Y' routing. An agent must infer the boundary from the 'no findings, no evidence' caveat.

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