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

Annotations declare readOnlyHint=true, yet the tool's stated purpose is creating a persistent monitor, which is unambiguously a state-mutating write. The description directly conflicts with the annotation, and no other behavioral context (persistence, side effects, resource creation) is offered.

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?

A single short, front-loaded sentence with no wasted words. It is appropriately terse, though at the cost of any behavioral or usage detail.

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 7-parameter tool with nested objects and an output schema, one sentence is thin. It omits that target_type drives which other parameters matter, that notification.webhook_url must resolve publicly, and cadence bounds, leaving the agent reliant on schema and contradicting annotations.

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% and the nested sitemap and notification objects are fully documented in the schema, so the schema carries parameter semantics. The description adds nothing about target_type coupling, cadence, or webhook requirements beyond restating the target modes.

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 ('Create a website-change monitor') and clarifies the two target modes (page or sitemap). Sibling differentiation is implicit via the monitors_* family, but the description never names the sibling operations it complements.

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?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as monitors_update or monitors_list. The agent is told what it creates but not when this is the right tool versus the rest of the monitors_* family.

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