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

The description adds a valuable behavioral trait beyond the annotations: the 50-result cap and the non-final 'preview' nature of the call. Annotations already provide safety-related hints (openWorldHint, destructiveHint), and while readOnlyHint=false is slightly awkward for a 'preview' operation, there is no direct contradiction.

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?

A single, front-loaded sentence with no redundant words. It states the purpose, scope, limit, and intended position in the workflow efficiently.

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 preview tool with a fully described filter schema, the description provides essential invocation context: what it does, the limit, and when to use it. Since there is no output schema, it could optionally describe the exact fields returned, but the core call context is 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 describes every filter field with 100% coverage. The description refers generically to 'a filter' and does not add parameter-level meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

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 ('Preview'), a clear resource ('companies'), and a concrete bound ('up to 50'). The phrase 'before creating a reusable company list' ties it to the company_lists workflow and differentiates it from both generic company search and the sibling count_preview tool.

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?

Clear usage context is provided: use this tool to preview matching companies before creating a reusable company list. It does not explicitly name alternatives or exclusion conditions, so it stops short of a fully prescriptive when-to-use/when-not-to-use statement.

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