Advanced: raw runtime_run

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

Annotations already declare readOnlyHint=false. The description adds governance-related behavior: it is 'DecisionGATE-admitted' and 'not a backdoor,' meaning it is still subject to policy checks. This is useful context but does not disclose side effects, state changes, or error behavior beyond the annotation.

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 compact—two sentences with no filler. It front-loads the '[advanced/internal]' label and the core governance message. Brevity is achieved, though at the cost of semantic clarity.

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 four parameters, no output schema, no parameter documentation, and no description of return values or failure modes, the description is severely incomplete. An agent cannot construct a correct invocation or understand the tool's behavior from this text alone.

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 0% and the description makes no mention of slug, op, payload, or session_id. There is no explanation of what these parameters mean, how they relate to the execution, or what valid values look like. The agent is left entirely to infer parameter semantics from names alone.

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 labels the tool an 'Advanced exec façade' but never states what it executes, what resource it operates on, or what outcome it produces. The phrase 'raw runtime_run' largely restates the tool's name, and while it distinguishes itself from fraggate_call, it fails to define its actual function.

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 says 'Prefer fraggate_call,' which gives an alternative and a clear preference. The '[advanced/internal]' tag signals restricted usage context, and 'not a backdoor past the door' clarifies it should not be used to bypass governance. However, it does not specify exactly when an agent should choose this over its siblings.

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