create_connection

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

With no annotations, the description must carry behavioral disclosure. It does disclose the write-access prerequisite and that read-only sessions refuse the operation. However, it omits other behavioral traits such as return value expectations (despite an output schema), potential side effects, or failure modes for invalid config. Coverage is partial.

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 tightly structured: a one-sentence purpose, a critical permission note front-loaded, then a clean arg list. No wasted words; every sentence earns its place. The write-access caveat is placed before the args, ensuring the agent sees it first.

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?

Output schema exists, so return values need no explanation. However, the description does not address how config depends on connection_type (which could vary significantly), nor does it point to get_connection_types for a list of valid types. The open-ended config object with additionalProperties true creates ambiguity that the description only partially mitigates.

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 0%, so the description must compensate. It provides meaningful explanations for all three parameters: name ('human-readable'), connection_type ('one of supported types' with examples), and config ('connection-specific configuration' with host, port, credentials). This adds value beyond the bare schema, though it could list supported types or link to get_connection_types for completeness.

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?

States a specific verb and resource: 'Create a new data connection.' This clearly distinguishes it from sibling creation tools like create_pipeline and create_transformation. The purpose is unambiguous and directly actionable.

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 no guidance on when to use this tool versus alternatives such as preview_connection or get_connection. It only mentions permission requirements (write access) but does not contextualize selection among siblings or note exclusions. The agent must infer usage from the name alone.

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