create_connection_link

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), the description discloses that OAuth credentials, provider calendar names, and event data never reach the agent, and that the secret URL is returned only on first creation. That is substantive behavioral context about an inherently stateful, non-idempotent handoff.

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 purpose is front-loaded and each sentence carries load (handoff rule, credential boundary, reuse fallback). The final reuse sentence is dense and depends on output field names not defined in the schema, slightly hurting readability.

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?

With no output schema, the description usefully covers the key return semantics (setup_url only on first creation) and the credential boundary, which is what an agent needs to act. It leaves the exact shape of the response and the meaning of reused less explicit than ideal.

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 100%, so calendar_id, capabilities, and publication_policy are already fully documented, making 3 the baseline. The description references reused and setup_url, which are response-side fields rather than input parameters, so it adds little meaning to the actual arguments.

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 action and resource: requesting human OAuth setup of Google Calendar or Microsoft Outlook for a Chronary calendar, producing a setup link. An agent can distinguish it from get_connection_link and cancel_connection_link, which retrieve or destroy the same resource.

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 clearly instructs the agent to give setup_url to a human and that the agent never receives credentials, and it specifies the reuse branch (reused=true with null setup_url → retain or cancel and recreate). It stops short of explicitly naming the sibling tools (get/cancel_connection_link) as alternatives.

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