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

Annotations declare non-read-only, non-destructive, non-idempotent behavior; the description adds important context beyond them: a draft is saved, nothing is scheduled, and the return includes the window in the user's time zone, next recurrence occurrences, affected status pages, subscriber email count, and a draft id. It does not cover draft persistence, visibility, or notification timing, but it is substantially more informative than the annotations alone.

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 sentences, front-loaded with the trigger and exclusion, followed by return and draft behavior. Every sentence adds selection or behavioral value, with no restatement of the title or schema.

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 12-parameter tool with no output schema and complex recurrence options, the description covers the trigger, draft-only semantics, and key return fields. It leaves out some possible details such as draft expiry, where the draft is stored, or whether subscriber notification is sent now or only counted, so it is strong but not fully complete.

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%, with every parameter documented inline, including enums and defaults. The description's phrases like 'once or on a schedule' and 'next occurrences of a recurring one' provide framing but no syntax or format detail beyond what the schema already gives, so 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?

States a specific verb and resource (draft a maintenance window) plus the exact scope: planned work on a site, once or on a schedule, optionally notifying subscribers. It also distinguishes itself from draft_incident_post for outages already in progress, so an agent can tell sibling tools apart.

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 names the triggering situation (user plans a deploy, upgrade, or migration and wants it marked as maintenance) and the exclusion (not for an outage already happening; use draft_incident_post instead). The note that it 'saves the draft and schedules nothing' also implicitly routes scheduling use cases to schedule_maintenance.

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