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

Annotations already declare readOnlyHint=false, idempotentHint=false and openWorldHint=true, but the description adds genuinely new operational context: each run consumes the monthly quota, runs execute serially (seconds to minutes each, several minutes for a whole site), and the result carries estimatedMinutes and tellUser so the agent should warn the user about a wait. This is exactly the extra cost/timing/cancellation detail annotations cannot convey.

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-loads the action and scope before cost, timing, and return handling, with no filler sentences. It is dense and em-dash heavy, and the quota/timing points could be tightened, but every clause carries information the caller needs.

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 still tells the agent what comes back (runIds) and which result fields to surface to the user (estimatedMinutes, tellUser), plus how to monitor or cancel the run. Nothing needed to invoke or narrate this non-idempotent, quota-consuming operation is missing.

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%, so the baseline is 3, but the description adds real semantics beyond the schema: a group run covers only that group's enabled monitors, while checkId runs a single monitor 'even if it's turned off' — a behavioral nuance not present in the schema's terse 'Run only this monitor'.

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+resource ('Run a site's enabled monitors now') and immediately enumerates the three scoping modes (all enabled, one group, one monitor via checkId). An agent can distinguish this from siblings like list_runs or resume_monitor_group without opening a 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?

Gives clear triggers and routes follow-up work explicitly: 'Returns the runIds to follow with get_run or list_runs' and 'cancel_queued_runs stops the ones that haven't started.' It also warns about quota cost and wait time. It stops short of any explicit when-not-to-use or comparison against neighboring trigger-style tools such as start_safe_update or start_monitoring_for_goals.

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