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

Annotations already declare non-read-only, non-destructive, non-idempotent, so the safety profile is covered. The description adds genuinely useful behavior: the schedule targets the live build, ownership is implicit to the caller, and repeating schedules inside an automation either fire immediately (matching an existing schedule) or land in the draft and fire on activation — context an agent could not infer from the schema.

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 core action, then the operationally important detail. The revision/draft sentence is long and niche, but it is conditioned ('On a team with revisions') rather than bloating the general case, so it largely earns its place.

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 9-parameter mutation with 11% schema coverage and no output schema, the description should explain at minimum how frequency interacts with cron/day/time/day_of_month and what timezone format is expected. It covers the automation-revision behavior well but leaves the actual scheduling payload undefined.

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 only 11% across 9 parameters, so the schema carries almost no semantics for cron, time, day, day_of_month, frequency, recurring, or timezone. The description mentions no parameters at all (the referenced `pending_change` isn't even an input), leaving the caller with zero guidance on how frequency='custom' relates to cron vs. day/time.

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 ('Create a schedule for an agent') and adds scope that matters: the schedule fires against the agent's live build and is owned by the authenticated user. It doesn't explicitly name updateSchedule/deleteSchedule as the alternatives, so it stops short of full sibling differentiation.

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 real context for when the created schedule takes effect (live build; automation revisions join draft vs. immediate fire), which implicitly tells the agent when this tool is the right one. But there is no explicit 'use updateSchedule to modify an existing schedule' or exclusion guidance, so usage is inferred rather than stated.

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