Shield Break Glass

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

Annotations already indicate destructive behavior. The description adds context about required authorization (admin role, shield:write scope, audit reason), which is valuable for safe invocation. No contradictions with annotations.

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?

The description is a single, succinct sentence that covers the key points without unnecessary words. It is front-loaded with the action, then requirements.

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 destructive tool with an output schema, the description covers purpose, requirements, and mandatory parameters. It does not detail return values (handled by output schema) and is sufficiently complete for safe use.

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%, so the description adds minimal new meaning. It mentions admin role and shield:write scope, which align with parameter descriptions but do not exceed them. 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 ('Run Shield break-glass override'), specifying a distinct verb and resource. It differentiates from sibling tools like shield_start, shield_status, and shield_unblock by focusing on an emergency override scenario.

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 provides explicit prerequisites (admin role, shield:write scope, audit reason), guiding when to use the tool. However, it does not mention when not to use it or suggest alternatives, such as shield_unblock for non-emergency cases.

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