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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavior note — authentication is supplied via auth-profile references rather than inline secrets — but 'safe configuration' is vague, and nothing is said about uniqueness of name, idempotency, or failure modes.

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?

One front-loaded sentence with no padding or repetition. It is efficient, though the brevity is partly under-specification rather than disciplined concision.

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?

An output schema exists so return values need not be described, but for a creation tool with 7 parameters, three required, nested per-environment objects, and zero schema descriptions, the definition leaves too much unexplained to invoke it confidently. The critical concept — that base URLs and auth profiles are keyed by environment — is never surfaced.

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 description coverage is 0% across 7 parameters, including nested environment-keyed maps and the runtimeKind enum, yet the description only obliquely hints at authProfileIdByEnvironment via 'auth-profile references'. It does not explain the environment-key map semantics, the http/llm runtime distinction, or the optional llmProviderConfigIdByEnvironment, so it fails to compensate for the documentation 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 and resource ('Create an upstream connection'), which is distinct from connection_get, connection_list, and connection_update. However, it offers no explicit sibling differentiation beyond the verb, and 'upstream connection' is left unpacked for an agent unfamiliar with the domain.

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?

There is no guidance on when to create versus update an existing connection, no prerequisites (e.g., that an auth profile must exist first), and no mention of alternatives such as api_create or endpoint_create. The agent is left to infer context from the tool name alone.

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