Poll a human-calendar setup request to retrieve provider-neutral status and the connection ID when complete, without replaying the setup URL or exposing calendar data.
Poll a human-calendar setup request. Returns provider-neutral status and resulting connection ID when complete, but never replays the bearer setup URL or exposes human calendar data.
| Name | Required | Description | Default |
|---|---|---|---|
| connection_link_id | Yes | Connection setup link ID |
Changes observed during successful MCP inspections.
v1.5.3Input schema / properties / connection_link_id / formatAdded value: +"starts_with"v1.4.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), so the description is freed to add non-obvious behavior. It does: it discloses that the bearer setup URL is never replayed and human calendar data is never exposed, which is a meaningful security constraint an agent could not infer. It doesn't state what status values look like or terminal vs pending states.
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?
A single dense sentence, front-loaded with the action, followed by the return/behavior caveats. No filler and nothing repeated from the schema or annotations.
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 present, the description correctly carries the return-value burden, describing status plus resulting connection ID and ruling out the setup URL and calendar data. It could go further by enumerating possible status values, but combined with the annotations it is largely complete.
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%, with connection_link_id fully documented including its prefix pattern, so the schema carries the parameter burden and baseline is 3. The description notes the ID relates to a 'connection' but adds no format or sourcing detail beyond the schema.
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: 'Poll a human-calendar setup request.' The polling verb cleanly distinguishes it from create_connection_link and cancel_connection_link, which are the lifecycle siblings. It stops short of naming those siblings explicitly, so it lands at 4 rather than 5.
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?
'Poll' implies the tool is for repeatedly checking an in-flight setup, which is useful implied usage. However, there is no explicit when-to-use versus create_connection_link/cancel_connection_link guidance and no stated precondition that a connection_link_id must already exist from create_connection_link.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.