failure_rehearsal

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

Annotations already declare readOnly/destructive=false/idempotent, and 'never executes it' reinforces rather than contradicts them. The description adds genuine behavioral context about the artifact's shape (success criteria and stop conditions must be present), though it says nothing about output format or constraints on generated drills.

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?

A single front-loaded clause carrying the verb, the resource, the required design qualities, and the execution boundary. Nothing is wasted and nothing is buried.

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?

The output schema exists, so return values needn't be explained, and the non-execution boundary is covered. But with three required, undescribed parameters and no guidance on how the drill content relates to 'operation'/'target', the definition is only minimally sufficient for correct invocation.

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?

Three required parameters with 0% schema description coverage, and the description never mentions any of them. 'operation' and 'target' are undefined in both places — an agent must guess whether operation is a command, an API call, or a described workflow — and the failure enum meanings are only inferable from their names.

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 ('Design a controlled failure drill') plus the key attributes (observable success criteria, stop conditions) and an important boundary. It is clear what the tool produces, but it never names a sibling (runbook, dr_strategy, postmortem) to differentiate itself from adjacent artifacts.

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?

'never executes it' is an explicit exclusion that tells the agent not to expect an actual drill run, which is a real usage boundary. However, there is no positive statement of when to reach for this versus runbook or dr_strategy, so the routing guidance is partial.

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