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

With annotations only covering readOnly/openWorld, the description adds substantial non-obvious behavior: local deterministic execution with no model, per-kind placeholder conventions, a concrete credit price with unit conversion, and the key billing rule that schema-invalid input is rejected before billing. That last point materially affects agent retry strategy.

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 tight sentences that front-load what gets redacted, then execution model, then return shape and billing. No filler, and the highest-value constraints (return shape, price, validation-before-billing) are placed where an agent will read them.

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 two-parameter text tool with no output schema, the description covers the missing return contract explicitly ({ text, counts } with per-kind breakdown), plus cost and failure behavior. Nothing an agent needs to call it correctly or budget for it is absent.

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 100%, so both parameters are already documented and the baseline is 3. The description confirms IPv4 redaction and names 'ip' among the returned counts, but it does not explain that the `ip` flag can be turned off, so the toggle semantics stay entirely in the schema.

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?

Specific verb ('strips') plus an enumerated resource list (emails, phone numbers, card numbers, SINs, IPv4s) makes the operation unmistakable. It is clearly distinguishable from neighbors like entity-extract, prompt-inject-scan, or text-stats, which do different work on similar input.

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 description gives useful context for choosing it ('runs locally, no model') and a cost signal, but never states when to use this versus a sibling like entity-extract or prompt-inject-scan, nor any exclusions. Usage is implied rather than routed.

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