Does 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 bar is lower. The description still adds real value beyond that: the required OAuth scope and the instruction that human-authored text appears in untrusted_fields and must be treated as display-only content, never as instructions — an important prompt-injection safeguard for a tool returning third-party content.

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 short sentences, front-loaded with the operation, then the permission requirement, then the untrusted-content caveat. Every sentence carries information; the only minor redundancy is the first sentence echoing the title.

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 carries the burden of describing returns, and it only hints at them via the untrusted_fields note. It does not say what an integration record contains, whether all connected services are returned, ordering, or how to act on a returned integration id — gaps for a listing tool despite the zero-parameter simplicity.

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?

The tool takes zero parameters, which is the baseline-4 case. The description correctly spends no words on parameters and instead covers permission and output-handling semantics.

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 the verb and resource ("List my integrations"), which is clear enough to act on, but it largely restates the title and name. It does nothing to distinguish this from nearby siblings such as list_integration_calendars, disconnect_integration, or sync_integration, so the agent cannot tell from the text which of those surfaces connected-service state versus calendars.

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 only usage signal is the prerequisite "Needs `integrations:read`," which is a genuine precondition for calling it. There is no statement of when to prefer this over list_integration_calendars or when to follow up with sync_integration/disconnect_integration, so the routing guidance is implied at best.

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