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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the lower bar applies. The description does add real value with the partial-update guarantee ("Only the fields given change") and the return value (next run in UTC and the schedule's timezone). It does not disclose what is lost or risked when overwriting instructions or schedule, nor any permission requirements, which matters for a destructive non-idempotent mutation.

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 tight clauses: what changes, which fields, and what is returned. The partial-update guarantee is front-loaded immediately after the field list, and no sentence is filler.

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?

There is no output schema, and the description still covers the return value, plus partial-update semantics and the nested schedule reference. The remaining gap is behavioral context around pausing/resuming and permissions, which is meaningful but secondary given annotations carry the safety profile.

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 29% across 7 parameters (schema only documents agent_id and task_id), so the description must compensate. It does name five of the mutable fields and usefully delegates the nested schedule object's shape to schedule_agent_task, but adds no semantics for max_runs bounds or status transitions beyond the enum, leaving it adequate rather than complete.

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 plus resource ("Change a scheduled task") and enumerates exactly which fields are mutable: title, instructions, schedule, max_runs, status. It also disambiguates from get_agent_task/schedule_agent_task by describing the update operation and by pointing at schedule_agent_task for the schedule shape.

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 is implied rather than stated: "Change a scheduled task" and the pointer to schedule_agent_task for the schedule object shape give context, and status active/paused hints at pausing. However, it never says when to use this vs. stop_agent_task, run_agent_task_now, or archive_agent_task, nor whether there are preconditions (task must exist, owner permission).

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