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

Goes well beyond the annotations: it discloses the exact down/up determination rule (two consecutive failures, 10s timeout, missing expect_text), the alert routing per state change, certificate expiry monitoring, and the billing model including 'nothing if it fails'. It also notes the call itself performs the first check, which is a non-obvious side effect.

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 behavior, then cost, with no filler sentences. There is mild redundancy in restating pricing twice ('$0.50 a month per monitor, renewed from the balance' and 'Costs $0.50 per call'), and the semicolon-chained sentence is dense, but nothing is wasted.

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 mutation tool with no output schema, the description covers side effects, alerting, billing, and failure detection thoroughly. The notable gap is what the call returns (monitor id/object) that the agent would need to later call uptime_get_monitor or uptime_update_monitor.

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 86%, so the baseline is 3, and the description still adds real semantics: what expect_text means for up/down determination, that named channels plus the owner get alerted on transitions, and that intervals are server-side polling frequencies. It does not explain the interaction between public/status page or when email_alerts and notify_channels overlap, keeping it short of a 5.

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 concrete action and resource: create a recurring server-side check of a page at a chosen interval, with uptime/down semantics and certificate watching. It is clearly a creation tool, though it never explicitly contrasts itself with uptime_update_monitor or uptime_get_monitor, leaving that differentiation to the name.

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?

Usage context is implied through the failure policy and pricing, which make it clear this is for standing up new monitoring rather than one-off checks. However, there is no explicit 'use this instead of uptime_update_monitor when...' guidance and no mention of prerequisites such as channels needing to exist first (that is only hinted at in the schema's reference to notify_add_channel).

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