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

With no annotations, the description carries the full burden, and it does disclose the critical non-obvious trait: this read-looking call "triggers one processing tick," i.e. it mutates state. That is genuinely valuable. It omits polling cadence/rate limits, error or terminal states, and permission requirements for a tool that advances a workflow.

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?

One dense sentence, front-loaded with the action, then the side effect, then the return shape — no filler. Every clause carries distinct information.

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, the description usefully summarizes the return value (steps, dns_records, cert validation + routing), which is a real plus. But for a state-advancing polling tool with a required identifier, it leaves out polling semantics, terminal-state handling, and parameter meaning, so it is only adequate.

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 0% for the single site_id parameter, so neither structured data nor the description explains what site_id is (site identifier vs. domain vs. setup record id). The description does not compensate at all, leaving the required argument semantically undocumented.

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?

Specific verb+resource: "Poll custom domain setup progress" clearly identifies a status-check on a custom domain, distinguishable from connect_custom_domain/disconnect_custom_domain which initiate or tear down setup. It also names the return payload (steps and dns_records), so an agent knows what it gets. It stops short of explicitly saying which sibling starts the setup this tool polls.

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?

"Poll" implies repeated invocation while setup is in flight, which is useful implied guidance, but there is no explicit statement of when to call it, when to stop polling, or when to prefer connect_custom_domain. The agent must infer the lifecycle position.

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