trigger_update

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavior beyond that: changes are applied immediately and firing rules restart, which materially affects how an agent should sequence calls. It stops short of describing validation failures, partial-apply behavior, or auth requirements, so it is strong but not exhaustive.

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 sentences, front-loaded with the action and the changeable fields, then the effect, then the routing rule. The field list is dense but each item earns its place as valid targets. Minor cost: the long comma-separated enumeration is harder to scan than a short structural hint would be.

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 two-parameter mutation with nested objects, the description covers what can change, when changes take effect, and where to go for the excluded cases. With full schema coverage and no output schema, little is missing. It could still say whether a call is atomic or whether unknown fields are rejected, but nothing an agent needs to invoke it correctly is absent.

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% and the schema already explains the changes object shape and null semantics. The description nonetheless adds value by enumerating which nested paths are legal targets (probe.params, probe.timeout, target.kind/cwd, etc.), which the schema only gestures at with 'shaped like the definition'. It does not go deeper into per-field formats, but the enumeration is a real constraint an agent would otherwise have to guess.

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?

Opens with a specific verb and resource ('Change an existing trigger') and immediately enumerates the exact fields that can be modified (probe.params, probe.interval, policy, action, target, notify, name, intent). It also explicitly contrasts itself with the sibling trigger_draft, so an agent can distinguish the two without reading either 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?

States the boundary condition directly: 'To change the probe code or the mode, use trigger_draft with replace=true instead.' This names the alternative tool, the parameter to set, and the exact cases that should be routed elsewhere, leaving nothing to inference.

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