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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds beyond that: returns null for non-kill-chain alerts and requires a specific scope. This provides useful context about edge cases and permissions, though it omits details like rate limits or error handling.

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?

Two sentences: first concisely defines the purpose and output, second adds an edge case and required scope. No fluff, front-loaded with the core action. Every sentence earns its place.

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?

With a single parameter, no output schema, and annotations covering safety, the description fairly explains the return (null for non-kill-chain) and mentions the output shape (pattern, severity, tool-call ids). It could be enhanced by describing the response structure more, but overall it's sufficient for a simple, read-only fetch.

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 schema already describes the alertId parameter as a UUID from list_incidents. The description does not add any extra semantics or usage guidance beyond what the schema provides. Baseline 3 is appropriate.

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?

The description clearly states the action (fetch kill-chain finding), the resource (alert), and the key details returned (multi-step attack pattern, severity, tool-call ids). It distinguishes from siblings like axiorank_list_incidents by focusing on evidence retrieval. The note about null evidence for non-kill-chain alerts adds precision.

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?

The description explicitly requires an alert ID and the `logs:read` scope, which guides invocation. It implicitly suggests use when kill-chain details are needed, but does not provide explicit when-not-to-use or mention alternative tools like list_incidents. Given sibling names, the context is clear enough.

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