trigger_tune

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

Goes well past annotations (which only say non-read-only, non-destructive) by disclosing the stateful semantics — no new baseline and no re-fire for an already-holding condition — plus the side effect that the user is told what changed and why. The monotonic tightening constraint is established as a behavior, not just a schema rule.

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 the core action and state guarantee, then the allowed levers, then the exclusion — a sensible order with no filler sentences. The opening is dense and parenthetical-heavy, bordering on a run-on, which costs a point.

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 with no output schema, the definition covers scope, direction of change, state preservation and user-visible consequences, which is what an agent needs to invoke it correctly. Return behavior and failure modes (e.g. a trigger already paused) are left unstated but are low stakes here.

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 earns a step up by enumerating the five levers in plain language and framing the one-directional constraint ('check less often, wait longer ... allow fewer fires') as a deliberate safety principle rather than an isolated per-field note. It does not add format details beyond what the schema already gives.

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?

Specific verb phrase ('Make a trigger ... quieter') plus resource and the exact dimension of change (check interval, cooldown, hold time, fire cap, pause). It explicitly draws the boundary against trigger_update, so an agent can distinguish it from siblings without opening schemas.

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?

Strong when-to-use ('the one change allowed while handling a fire, and then only for the trigger that fired') and an explicit when-not with the alternative named ('anything that makes a trigger more sensitive goes through the user and trigger_update'). The gap is the 'pause' option, which overlaps the sibling trigger_pause and is never routed or differentiated.

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