conduyt_ai_plan_actions

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

With no annotations, the description carries the full burden and does so: it declares the call is non-mutating, that resolution is scoped to records the caller can see, that results may come back with issues such as an ambiguous name, that the confirmationToken is single-use and bound to that exact action set, and that the actions array must be returned unmodified. This is exactly the behavioral context an agent needs to avoid corrupting the token contract.

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 the verb and resource, and the safety/token contract follows immediately. It is a dense single flow with one long parenthetical list of action types; every clause earns its place, but the packing slightly hurts scanability.

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 explain returns and it does: resolved actions marked ready or with an issue, plus a single-use confirmationToken bound to that set. Combined with the three-parameter, fully documented schema, an agent has everything needed to call it correctly and to chain into execute_actions.

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 description coverage is 100%, so dealId and contactId are already documented in the schema, and the description adds little param-specific detail beyond noting resolution is limited to visible records. It does effectively characterize `message` as free-form rep language via the quoted examples, but that is largely illustrative of purpose rather than parameter semantics. Baseline 3 is appropriate.

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?

Specific verb+resource: turns a natural-language request into a preview of concrete CRM actions, with the exact action types enumerated (tasks, callbacks, notes, appointments, tags, stage moves, SMS/email drafts). The parenthetical example requests make the input domain unmistakable, and it is clearly distinct from conduyt_ai_execute_actions, which applies the plan.

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 states when to use it (plan/preview) and names the follow-up tool and the exact condition for using it: pass the unmodified actions array plus the single-use token to conduyt_ai_execute_actions. It also states a negative constraint (nothing is written here, drafts are never sent), leaving nothing to inference.

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