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

Annotations declare readOnlyHint=false and openWorldHint=true but give no reason; the description explains why this read-like operation is flagged as a write — it is paid via x402 ($0.01 USDC on Base) and returns a payment challenge instead of autonomously spending funds. It also discloses the heuristic/comprehensive limits and that matched values are withheld. This is exactly the extra context annotations cannot carry.

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?

Four tight sentences, front-loaded with the cost and payment behavior — the single most decision-relevant fact — followed by output semantics and scope caveats. Minor redundancy between 'PAID $0.01 USDC on Base via x402' and 'returns a payment challenge', but nothing 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?

An output schema exists, so return values need not be spelled out, and the description still usefully characterizes them as classifications and positions. Cost, privacy behavior, accuracy limits, and the no-autonomous-spend guarantee are all covered; only the mechanics of satisfying the payment challenge (handled by sibling x402 tools) are left 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?

Only one parameter, text, and schema description coverage is 100% with a documented 65536-byte cap. The description adds nothing about the input beyond what the schema already states, so the baseline of 3 applies rather than a penalty.

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?

States a specific verb and resource: 'Detects selected personal-data patterns and returns classifications and positions, not matched values.' The output-privacy distinction ('not matched values') plus the 'heuristic, not comprehensive' scope note make the tool's behavior unmistakable. It does not, however, name or contrast itself with the adjacent secret.scan sibling, which is the nearest alternative.

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 context is only implied ('detects personal-data patterns' → use when you need PII detection in a text blob), and no when-not-to-use or alternative (e.g. secret.scan for credentials) is given. It does supply one genuinely useful precondition — that invoking it returns a payment challenge rather than a result — but that is a cost/prerequisite note, not routing guidance.

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