create_connection_link

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

The description adds significant behavioral context beyond annotations: agents never receive credentials or event data, the secret URL is returned only once, and human involvement is required. No contradictions with 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?

Three sentences with no redundancy. Front-loaded with the core action. Every sentence adds value: action, human involvement, security constraints.

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?

The description explains the outcome (setup URL returned once) and key constraints (human only, no credentials). With no output schema, it adequately covers the tool's behavior for an agent to use correctly.

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 100%, so the description does not need to elaborate on each parameter. It provides context that aligns with parameter purposes but adds no extra detail beyond the schema descriptions.

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 verb 'Request human setup' and identifies the resources (Google Calendar or Microsoft Outlook for a Chronary calendar). It distinguishes the tool from siblings by emphasizing human involvement and the one-time nature of the setup URL.

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 tells the agent to give the setup_url to a human and that agents never receive credentials or data. This implies when to use (human setup needed) and when not (agent-only operations), but does not explicitly mention alternatives like cancel_connection_link.

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