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

Annotations already declare non-destructive, non-idempotent, open-world behavior, but the description adds context annotations cannot express: watches consume no monitor quota, a site is capped at 20, and the call saves a plan while changing nothing in the account. It also previews the return content (today's values plus the decisions to surface), so the agent knows what to do with the result.

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 trigger condition, and every sentence carries usable information (scope, return shape, quota cost, side effects, exclusion). It is dense—the return sentence crams values and decisions together—but there is no 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?

With no output schema and a nested 'answers' object, the description carries the burden well: it describes what comes back, how the decision loop works across calls, and what side effects to expect. An agent can sequence this call and the follow-up without further information.

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 100%, so the baseline is 3, but the description adds genuine meaning: omitting record types means 'see them all and decide,' and the 'answers by decision id: record_types, alert_on' semantics are explained in prose as the two questions to put to the user. That goes beyond the schema's one-line parameter notes.

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 (plan a DNS watch) and immediately scopes it with concrete examples: MX, _dmarc, SPF, and the CNAME a subdomain points at. It also explicitly separates itself from the site-uptime/DNS-health/certificate territory, which an agent could otherwise confuse with track_subdomain_certificate or diagnose_site.

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?

The opening clause gives a clear triggering condition ('when the user wants to know if DNS records change or stop resolving'), and the closing sentence gives an explicit when-not with a named alternative surface (FlareWarden's existing uptime/DNS health/cert checks). What is missing is a named next step for committing the plan (add_dns_watch), which the agent must infer from the plan_id/answers flow.

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