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

Annotations (readOnlyHint=false, destructiveHint=false) are enriched by the description: it discloses that the tool starts an Apify Actor, may consume Apify usage, waits up to 60 seconds, and returns a bounded result set while 'without changing the source list.' This directly addresses side effects and non‑destructive behavior beyond what the flags alone imply.

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?

Two sentences, no filler. The purpose is front‑loaded, then constraints and side effects. Every token earns its place, and it avoids restating obvious parameter details already in the schema.

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 complex tool with 11 parameters and two modes, the description covers the essential operational context (side effects, limits, non‑destructiveness) but does not explain the distinction between screen and filter modes or the shape of the returned records. However, the schema descriptions handle those aspects thoroughly, so the description is adequate for an experienced agent.

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 description coverage is 100%, and each parameter already has a rich, explanatory description (e.g., mode, enrichNpi notes, samApiKey secrecy). The tool description only summarizes the parameter space ('by name, valid NPI, state, specialty, or exclusion type') without adding detail, so it stays at the baseline 3 for a fully‑documented 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?

The description states a specific verb ('find review candidates') and a concrete resource ('HHS-OIG LEIE'), and lists the search dimensions (name, NPI, state, specialty, exclusion type). This clearly distinguishes it from sibling tools that query other registries (EPA, restaurant inspections, etc.) without needing to open any schemas.

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 explicitly says when to use the tool ('Use to find review candidates') and gives exclusions: 'Do not treat a candidate match as identity adjudication or use this tool for facility licensing.' It does not name an alternative sibling, but the sibling set is clearly domain‑distinct, so usage context is sufficient. Operational guidance (waits up to 60s, returns ≤1,000 rows) reinforces expected usage.

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