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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, but the description adds meaningful context they do not carry: checks and alerts stop entirely, and settings plus history are preserved. That 'reversible state change, nothing lost' framing is the key behavioral fact an agent needs before calling it.

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?

Two short sentences, both front-loaded with the primary effect first and the persistence guarantee second. No filler and nothing restated from structured fields.

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 one-parameter state-toggle tool with full schema coverage, annotations covering the safety profile, and no output schema, the description supplies everything needed: what stops, what is retained, and when the effect ends.

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?

There is a single required parameter and the schema already documents it at 100% coverage ('Monitor id from monitor_list'). The description adds nothing about the parameter, so the baseline 3 applies.

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 gives a specific verb and resource ('Stop checking a monitor') plus the concrete effect ('no checks, no alerts') and the boundary condition ('until it is resumed'). An agent can tell this apart from monitor_resume, monitor_update, and monitor_get without opening any schema.

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?

'until it is resumed' implies the inverse operation (monitor_resume), which is a helpful implicit pointer, but the description never states when to prefer pausing versus updating or deleting a monitor. Usage is inferable but not spelled out.

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