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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), and the description adds the details an agent actually needs beyond that: the run is refused if the automation is active, the change is reversible from the Archive, and the owner is emailed. The reversibility claim is consistent with destructiveHint=false, and the idempotency hint is not contradicted.

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?

Five short sentences, front-loaded with the action and its scope, then the precondition, then the notification and confirmation gate. No restated title, no filler, and the most decision-relevant constraint (pause first) appears before the softer context.

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 one-parameter mutation with no output schema, the definition covers everything needed to call it correctly: required prior state, blast radius, reversibility, side effect (owner email), and a confirmation requirement. Annotations carry the safety hints, so nothing material is left unexplained.

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?

With one parameter at 100% schema coverage, the schema already explains where automation_id comes from. The description only obliquely enriches its meaning by noting an automation spans 'every account it runs on', but gives no format or sourcing detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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 and resource ('Put an automation away') plus the exact scope ('on every account it runs on') and the observable effect ('stops replying and leaves the list'). That distinguishes it cleanly from sprkly_delete_scheduled_post, sprkly_update_automation, and sprkly_pause_automation in the sibling list.

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 an explicit precondition with the alternative to use instead: 'An automation that is on is refused: pause it first with sprkly_pause_automation.' It also states an explicit confirmation gate: 'Only when the user asks.' Both when-to-use and when-not-to-use are covered.

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