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

Annotations already declare destructiveHint=false and idempotentHint=true, but the description adds real substance: each run reads the workspace, its output is staged as a card until the user presses Run, and a run never sends or changes anything itself. That is exactly the side-effect disclosure an agent needs before scheduling autonomous work. It restates idempotency somewhat redundantly with the annotation and schema, which keeps it from a 5.

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?

The core capability and its cadence options come first, followed by behavioral guarantees, the quota, and idempotency. Every sentence carries information, though the idempotency sentence duplicates what the parameter description already says.

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 nested body object with four delivery/scheduling fields unmentioned and no output schema, the description leaves the agent guessing about run_on, weekday, and the Slack/email delivery flags. It covers the conceptual model and limits well but not the full parameter surface.

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?

The description explains cadence values and gives the local_time/timezone format through the '08:00 on weekdays' example, which is useful beyond the raw regex patterns. However, with only 50% schema coverage on a 10-property nested body, it never mentions run_on, weekday, deliver_email, or deliver_slack, so several parameters remain undocumented in both places.

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 and resource — 'Schedules the agent to run an instruction' — and enumerates the cadence modes (once, daily, weekdays, weekly) plus a concrete example. It clearly reads as a creation tool, but it never names the neighboring tools (updateAgentSchedule, listAgentSchedules) that an agent would need to choose between.

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?

Usage context is implied through the morning-brief example and the 'Up to 10 open schedules' ceiling, which hints at when creation will fail. There is no explicit when-to-use/when-not guidance and no pointer to updateAgentSchedule for modifying an existing schedule, leaving the create-vs-update choice to inference.

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