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

Annotations only declare readOnlyHint=false and destructiveHint=false. The description adds the important behavioral fact that some outcomes silently move the lead's stage (won, trial_started, appointment_booked, not_interested, do_not_call), which the agent cannot get from the annotations. It does not state permissions or reversibility.

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 core action, then side effects, then the workflow. No filler or repetition.

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 and six parameters, the description covers the essential mutation semantics and the draft/confirm workflow. The gaps are minor: no mention of notes/direction behavior and no indication of whether the stage change is reversible via undo_last_change.

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 only 33%, so the description must compensate. It explains the outcome side effects and implies the follow-up parameter, but notes and direction are never mentioned, and there is no syntax guidance beyond what the schema's follow_up_at description already supplies.

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: 'Record a call with one of your leads', and it goes further by naming the conditional side effect (stage changes for certain outcomes). It never names a sibling such as call_history or top_leads_to_call, so the agent must infer the distinction from the resource itself.

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?

'Two-step: draft, then confirm' gives real procedural guidance for the confirm flag, but that is largely restated from the schema's confirm description. There is no guidance on when to use this tool instead of call_history or undo_last_change.

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