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

Annotations already declare read-only/idempotent/open-world safety, and the description goes further by explaining the return shape (per-state notice IDs and counts), the three-day pairing rule for WA/DE records, and the fact that paired dates may legitimately disagree with neither declared correct. It does not mention result caps, pagination, or cost of broad substrings. The 'notifying org may differ from breached org' note is genuinely useful disclosure.

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-loaded with the resource and scope, then layered caveats. Five dense sentences, though the 'non-match never means no breach' point appears both in the description and in the parameter description, and the closing caveat about notifying vs. breached organisation slightly undercuts the otherwise tight structure.

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 one-parameter search tool with no output schema, the description explains the returned structure (per-state IDs and counts, paired notices), the pairing rule, and the semantic limits of a non-match. It stops short of stating result-count limits or how pairs with dates beyond three days are surfaced.

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 the baseline is 3; the description additionally explains that matching is on public names only (withheld names are excluded from the index entirely, not just from results), which tells the agent that a withheld-name search returns empty rather than a false negative to be interpreted.

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 ('find'), a specific key ('public notifying organisations by name substring'), and an explicit corpus ('Washington, Delaware and California Attorney General breach-notice lists'). The state scope alone lets an agent distinguish it from the broader sibling `breach_notices` without opening either schema.

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 strong interpretive guidance on when NOT to conclude anything: non-matches never mean 'no breach' because of list coverage, reporting thresholds and name variation, and withheld names are never searchable. It never routes the agent to an alternative tool (e.g. `breach_notices`) for other jurisdictions, so selection guidance is contextual rather than explicit.

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