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

Annotations (readOnlyHint=false, destructiveHint=true) indicate this is a write operation with side effects. The description adds useful behavioral context beyond these: the mandatory user confirmation step and the nuance that omitting assistantConfigId selects platform defaults, not the organization's isDefault assistant. This provides meaningful safety and behavior details 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?

The description is compact—two sentences—with the primary purpose front-loaded and the critical assistant-config caveat placed second. Every sentence adds meaningful information without redundancy, making it easy for an agent to parse quickly.

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 the tool's complexity (10 parameters, nested objects, output schema), the description is thin. It doesn't explain how scheduling works (e.g., when scheduledAt is provided) or the role of idempotencyKey beyond the schema's own note. While the output schema covers return values, the description leaves flow details under-specified for a write operation with destructive annotations.

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 50%, meaning five parameters (caseId, scheduledAt, firstMessage, variableValues) lack descriptive schema text. The description partially compensates by mentioning 'assistant/case, message, and schedule' but doesn't elaborate on formats or semantics of those parameters. It repeats the assistantConfigId guidance already in the schema, adding limited new value.

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 clearly states the tool's purpose: 'Create or schedule a call' with explicit resource and action. It also lists the key components (destination, caller number, assistant/case, message, schedule) and distinguishes it from sibling tools like cancel_call by focusing on creation/scheduling.

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?

The description specifies a key usage condition: 'after explicit user confirmation' of all details. It also warns about the assistant selection behavior when assistantConfigId is omitted. While it doesn't explicitly name alternatives, the context makes it clear when to use this tool (for creating/scheduling calls) and implies that cancel_call is for the opposite action.

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