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

Beyond the annotations (readOnly=false, idempotent=true, destructive=false), the description adds real behavioral constraints: partial updates leave untouched fields alone, monitor kind is immutable, and moving via page_id requires ownership of both pages. It does not discuss failure modes or what happens when an invalid change is requested, keeping it short of a 5.

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?

Three short sentences, no filler, and the core update semantics are front-loaded ahead of the mode-switch and permission details. Every sentence 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?

For a 19-parameter mutation tool with full schema coverage and annotations but no output schema, the description covers the non-obvious traps: partial updates, immutable kind, cron/period interlock, and owner-only relocation. It is sufficient to call correctly, though nothing is said about error or validation outcomes.

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 100%, so the baseline is 3; the description still adds meaning by clarifying that cron and period are mutually switching modes rather than independent settings, and that page_id is an owner-gated relocation. It doesn't elaborate on other high-risk parameters such as channels replacement or cost_alert_usd, so it isn't exhaustive.

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?

"Change a monitor" names a specific verb and resource, and "Only the fields given change" immediately pins down PATCH-style partial-update semantics, which separates it from create_monitor/delete_monitor. It never explicitly routes the agent to pause_monitor, resume_monitor, or get_monitor, so sibling differentiation is implied rather than stated.

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?

It gives useful preconditions (owner-only page moves, kind immutability) and explains the cron/period toggle, but offers no explicit when-to-use versus alternatives such as pause_monitor or resume_monitor for state changes. The agent can infer update semantics but receives no exclusion guidance.

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