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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so 'It changes nothing' is largely redundant. What the description adds beyond structured data is the conditional shape of the answer: general info by default, system-specific record types/actions with the system argument, and account-scoped agent list with per-record-type access and running state only for a signed-in customer — an auth dependency nothing else discloses.

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?

Front-loaded with trigger conditions followed by return contents, then exclusions — a sensible order. It is dense but nearly every clause carries information; the leading parenthetical 'AI Agents (inside one system)' is the one fragment that adds little, and the return-contents sentence is long.

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?

For a single optional enum parameter with a full output schema and complete annotations, the description covers what the tool answers, how the answer varies by argument and by sign-in state, and which siblings handle adjacent jobs. Nothing an agent needs in order to call it correctly is missing.

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% and the single enum parameter is fully documented there, so the baseline is 3. The description still adds real meaning by explaining the behavioral consequence of supplying it — the answer narrows to exactly what an agent can do in that system and gains record types, actions and automation options.

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 names a specific verb and resource — it returns what an AI agent works in, what it reads, what it can do after approval, what it never does, and (with a system) that system's record types, actions and automation options. It explicitly distinguishes itself from plan_ai_agent and get_integration_options, so an agent can route correctly without inspecting 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?

It gives concrete trigger phrases ('what AI Agents is', 'which systems it works with', 'which AI agents their account has') and names two exclusions with the sibling to use instead: setting one up goes to plan_ai_agent, syncing records goes to get_integration_options. When-to-use, when-not-to-use, and alternatives are all present.

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