airbyte_trigger_clear

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

The annotations already convey destructiveHint=true and readOnlyHint=false. The description adds significant behavioral context: it resets cursors, does not re-read from source (requires a subsequent sync), requires a self-managed Airbyte deployment with direct API access, and is not available on Airbyte Cloud. These details go beyond the 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 efficiently structured with a clear opening action, separated sections for usage guidance, and concrete examples. Every sentence serves a purpose, and the most critical information (what the tool does and when to use it) is front-loaded. It is concise yet comprehensive.

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 (destructive operation on Airbyte), the description covers prerequisites (self-managed deployment, direct API access), constraints (not on Cloud), behavioral implications (no re-read, need subsequent sync), return value (job with ID and status), and provides examples. The presence of an output schema reduces the need to describe return format, and the description meets the completeness bar for an agent to safely invoke the tool.

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 has descriptive comments for each parameter (e.g., stream name, namespace, connection_id). The description reinforces this with practical examples showing exact parameter usage for single and multiple streams. Although the description does not systematically list all parameters, the examples and context (e.g., 'Each needs at least a name') add value beyond the 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 clearly states the tool 'clear destination data for one or more streams in a connection,' using a specific verb (clear) and resource (streams in a connection). It distinguishes itself from the sibling airbyte_trigger_refresh by explaining that a clear removes data and does not re-read source, unlike a refresh.

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 provides explicit guidance on when to use the tool (remove stale data, prepare for clean re-sync, clear after schema changes) and when not to use it (Airbyte Cloud, if re-read without deleting, if connection is running). It also names the alternative tool airbyte_trigger_refresh.

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