create_connection

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

Annotations only supply destructiveHint=false, so the description carries the real behavioral burden and does so well: it discloses a live credential test at creation time, the specific non-standard HTTP 460 'connection_test_failed' non-retryable failure mode, and that secrets in properties are forwarded but never echoed back. These are non-obvious traits an agent could not obtain from the schema or 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 safety-critical constraint is front-loaded with an explicit IMPORTANT marker, which is the right structure for a tool that must not be called speculatively. A few phrases ('confirmed live', the parenthetical quoting the error code) are slightly redundant but still earn their place by grounding the failure mode.

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 5-parameter mutation tool with no output schema, the description covers the highest-risk unknowns (live validation, failure code, secret handling). It stops short of describing what is returned on success beyond implying no secret echo, which is the main remaining gap.

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 40%, so the description should compensate. It adds genuine meaning for `properties` (may carry secrets such as an access key, forwarded to the API, not returned), but says nothing about project_id, name, or description, and adds nothing on datasource_type beyond the schema's own examples.

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 never explicitly states that the tool creates a connection object in a project; it only refers to 'this call' testing credentials 'at creation time' and to 'this tool's output'. The verb 'create' plus siblings like update_connection/delete_connection let an agent infer purpose, but the description itself is framed around a behavioral warning rather than a statement of what is created.

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?

It gives an unusually explicit when-not-to-use rule: no speculative use, no placeholder credentials, only genuinely reachable external-system credentials. What's missing is routing guidance toward siblings — e.g., using list_connection_types to discover a valid datasource_type, or update_connection for existing records.

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