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

Goes well beyond the readOnly/idempotent/openWorld annotations: it discloses the external data source (HIBP catalog), the shape of the results (dates, exposed data classes, account counts), the privacy scoping (no email ever requested), and a prompt-injection warning about third_party_fields written by others. That injection guidance is materially useful behavior an agent would not get from annotations.

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?

Front-loads purpose, then returns, then scope, then a safety directive — a sensible order with little waste. The final third_party_fields sentence and the awkward 'pass on personal_check:' clause are slightly dense and could be tightened without losing meaning.

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 compensates by naming the returned fields, and it covers scope limits and injection safety. The only gap is the ambiguous personal-email pointer, which leaves the precise alternative path slightly unclear for an agent deciding where to route.

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 already 100% for the single 'domain' parameter, so baseline is 3. The description earns above baseline by clarifying that the parameter is strictly a domain and that no email address is accepted or queried, which prevents a common misuse.

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 ('Check whether a domain appears in known public data breaches') and names the underlying source (Have I Been Pwned breach catalog). It also draws the line against the nearest sibling by declaring 'Domain-level only: no personal email is queried', which separates it from dp_check_email_security.

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?

Gives a clear when-not ('no personal email is queried') and points to an alternative route for personal email checks. However, the phrasing 'pass on personal_check: Have I Been Pwned's own site' is grammatically muddled and makes the exact hand-off less crisp than it could be.

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