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

The description goes well beyond the annotations, disclosing that it starts an Apify Actor with the caller's APIFY_TOKEN, may consume Apify usage, waits up to 60 seconds, returns at most 1,000 source-linked rows, and does not change the source list. These side-effect, timeout, and scope details are valuable and are not present in the annotations or schema.

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 sentences with zero filler: purpose first, exclusion caveat second, and execution semantics third. Every sentence earns its place and the most important scoping information is front-loaded.

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?

Given this tool's complexity—multiple modes, external APIs, API keys, and no output schema—the description holds back some context like the screen/filter mode distinction and optional CMS/SAM enrichment. The schema fills most gaps, but without an output schema a more explicit note on return record shape would have made it fully complete.

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?

The input schema already provides rich, near-100% descriptions for every parameter including mode, screenList, samApiKey, and enrichment flags. The tool description adds only a high-level summary of searchable dimensions, which is useful but does not meaningfully increase understanding beyond what the schema already provides.

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?

The description states a specific action ('find review candidates') and resource (HHS-OIG LEIE), and lists concrete search dimensions: name, valid NPI, state, specialty, or exclusion type. It also explicitly distinguishes the tool from identity adjudication and facility licensing, which clearly separates it from sibling tools.

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?

It tells the agent when to reach for this tool ('Use to find review candidates') and gives clear negative guidance ('Do not treat as identity adjudication or use for facility licensing'). It does not name an alternative tool for those excluded actions, so while the context is clear, the alternative path is left implicit.

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