Delete Alert

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

No annotations exist, so the description carries the full disclosure burden. It discloses the cascading destructive side effect ('this removes that saved search') and the confirm gate, which addresses the highest-risk behavioral trait. However, it does not state whether deletion is permanent/irreversible, what happens to dependent artifacts like triggered alerts, or what occurs if confirm is omitted — meaningful gaps for a destructive tool.

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?

Four short sentences, each earning its place: the core action, the key domain fact linking alerts to saved searches, the mandatory flag, and the conditional namespace guidance. The action is front-loaded and there is zero filler or repetition of schema content.

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?

Despite having no output schema and no annotations, the description covers purpose, side-effect scope, the required safety flag, and namespace disambiguation — giving all four parameters contextual treatment. Minor gaps remain (return behavior, irreversibility), but nothing an agent needs to invoke the tool correctly 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%, setting the baseline at 3. The description adds genuine meaning beyond the schema: it explains the disambiguation role of app/owner ('when the name exists in more than one namespace'), going beyond 'App context for lookup', and reinforces confirm as a mandatory safety gate rather than just a default value. This elevates it above baseline.

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 action on a specific resource ('Delete a Splunk alert') and differentiates itself from sibling tools by explaining the alert/saved-search relationship ('Alerts are saved searches, so this removes that saved search'). This directly distinguishes it from delete_saved_search and clarifies what it is not, so an agent can select it correctly after one read.

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?

Provides explicit invocation conditions: 'Requires confirm=true' states a mandatory precondition, and 'Use app and owner when the name exists in more than one namespace' gives a clear conditional for parameter selection. It stops short of a full routing contract — there is no explicit 'instead use X' or 'do not use when' — but the context is clear enough to use correctly.

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