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

Beyond the readOnlyHint=true and destructiveHint=false annotations, the description discloses a real behavioral nuance: for clay, lists are the tables registered on the Integrations page because Clay's API cannot enumerate tables, and webhook URLs are omitted from results. It also states the exact return fields (id and name), which an agent would otherwise need to discover. The 'Requires a connected integration' line adds an operational prerequisite not present in 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?

Five sentences, each contributing to purpose, clay exception, return shape, downstream usage, or prerequisite. The core purpose is front-loaded, and the clay edge case is contained in a separate sentence without bloating the main message. Slightly dense, but no redundancy.

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 list operation with no output schema, the description covers what an agent needs: provider dimension, clay-specific source of truth, returned fields (id, name), how to consume the result, and the integration prerequisite. The only missing elements are standard list-tool details like pagination or empty-result behavior, which are minor given the tool's simplicity. Annotations already establish the safety profile.

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 both parameters and enumerates provider (100% schema description coverage), so the baseline is 3. The description adds some color on the provider parameter by listing valid values and explaining clay's registration behavior, but it adds nothing about workspaceId beyond the schema's default note. Overall, the description enriches the provider semantics slightly without needing to compensate for a schema gap.

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 ('List'), a specific resource ('external provider's lead lists'), and names the exact provider parameterization (instantly, hubspot, clay). This clearly distinguishes it from internal lead-list tools like campaignstack_list_lead_lists by emphasizing 'external provider'. The clay-specific clarification reinforces the scope and avoids ambiguity.

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?

Provides clear context: it is for external providers only, requires a connected integration, and explains how the returned id is consumed ('Use the id as listId with campaignstack_add_lead_to_external_list or in an integration:add_to_list workflow node'). It does not explicitly name alternatives for internal lead lists, but the 'external' qualifier and provider enum make the intended use unambiguous.

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