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

The description discloses substantial behavior beyond annotations: a five-minute dedupe window, run.busy when another agency check is running, site_ids scoping that leaves other sites alone, effects on last_run_at, daily on-demand pass accounting, and a 12-per-site-per-day limit with run.limited. These are exactly the operational traits an agent needs.

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 main action and scope are front-loaded, and every clause carries operational meaning. The parenthetical busy-state and rate-limit details make it dense and somewhat long, but there is little wasted text.

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 complex fleet-wide backup monitor with no output schema, the description covers the critical decision-making behavior thoroughly, including dedupe, busy state, scoping, and quotas. It does not fully describe the response payload beyond run.busy, run.limited, and last_run_at, so a small completeness gap remains.

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 already 100%, but the description adds important semantics for site_ids: it scopes the check to only those sites, does not count as the global last check, does not consume daily on-demand passes, and is capped at 12 checks per site per day. This goes well beyond the schema's simple 'Check only these sites' wording.

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?

The description states a specific verb and resource: 'Run the backup monitor now across every connected site running SiteVault, UpdraftPlus or Duplicator and update backup alerts.' It also distinguishes itself from backup-triggering tools by saying it 'never starts a backup,' though it does not explicitly name or contrast with sibling status tools like recipe__backup_status.

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?

It gives clear usage context: run now, optionally pass site_ids to limit scope, and understand dedupe/busy behavior. It includes an explicit exclusion ('never starts a backup') but does not name alternatives such as fleet__trigger_backups or recipe__backup_status, so guidance is strong but not fully comparative.

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