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

The annotations only say readOnlyHint=false / destructiveHint=false / idempotentHint=false; the description supplies the substance behind them. It discloses that each plan persists as a new concept that is not yet a working agent, that nothing takes effect until the person opens the link and signs in, and that replanning creates a new concept and a new link rather than mutating the old one — which is precisely why idempotentHint is false and nothing is destructive.

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?

Usage and outcome are front-loaded in the first sentence, and nearly every clause carries distinct information (persistence, link, sign-in, immutability, defaults, prerequisite, exclusion). It loses a point for density and mild repetition — the person signing in and reviewing the setup is stated twice across nested clauses.

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 tool that creates a saved artifact with an external completion step, the description covers the prerequisite, the side effect, the follow-up action, and the stale-link hazard. An output schema exists, so return values need not be explained, and nothing an agent needs to call this 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%, so the baseline is 3, and the description goes beyond it by defining the empty-case behavior ('Without record types it plans reading every record type the system offers') and by pointing to get_ai_agent_options as the source of valid action-group names. It does not spell out defaults for change_record_types separately, but the added default semantics justify a 4.

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?

Names a specific resource (AI agent planning) and states exactly what the call produces: which record types it would read or change, action groups, and a pre-filled setup link. It also explicitly marks the sibling it is not ('Not for syncing records between two systems (use plan_integration)'), so an agent can route between them without opening either 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?

Gives a triggering condition ('Use when someone wants an AI agent inside one of their systems'), a concrete example utterance, an exclusion with the correct alternative (plan_integration), and a prerequisite step ('Call get_ai_agent_options with the system first when you do not know what it offers'). Both when-to-use and when-not-to-use are explicit.

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