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

Annotations only assert readOnlyHint, but the description discloses rich behavioral detail: the needs_reconnect flag on linkedin/google_calendar/fathom, the meaning of a missing key ('not checked, not disconnected'), and the two independent Slack flags with guidance on which to judge notification delivery by. This is exactly the context annotations cannot carry.

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?

Uses summary/returns structure with the actionable trigger conditions front-loaded; every sentence, including the Slack dual-flag caveat, prevents a concrete misuse and none is filler.

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?

No output schema exists, so the description must and does fully document the return shape, key semantics, edge cases (missing keys, needs_reconnect), and per-integration exceptions. An agent can call and interpret this tool correctly with no other source.

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?

There are no input parameters, so the baseline is 4. The description still adds value by enumerating the integration_id key space (gmail, outlook, linkedin, slack, googlesheets, salesforce, notion) that the returned dict is keyed by.

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+resource ('which integrations the account has connected') and pins the return key vocabulary to the same integration_id used by get_tool_connect_url, so the agent can distinguish it from sibling lookup tools without opening the schema.

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?

Explicitly names both triggering situations: before telling a user an integration is unavailable, and before minting a connect link for one the user claims is already connected. It even anticipates the likely wrong assumption ('it may already be active').

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