Eval

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

With no annotations present, the description must carry the full behavioral burden. It discloses that the tool is disabled unless explicitly allowed, which is useful, but says nothing about side effects, whether the backend code can mutate state, required permissions, error behavior, or security risk despite being an escape hatch for arbitrary backend expressions.

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 front-loaded sentence with no wasted wording, which is structurally concise. However, its brevity comes at the cost of useful detail, so it is efficient but not maximally effective for such an open-ended tool.

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?

Given that this is an advanced escape hatch with no annotations, no output schema, and arbitrary backend-defined input, the description is materially incomplete. It omits return behavior, failure modes, safety considerations, and when the explicit allowance is required, leaving an agent without enough context to invoke it confidently.

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%, and the single 'code' parameter is already documented as 'Backend-specific expression or statement.' The description adds no additional meaning about expected syntax, format, or constraints, so the baseline of 3 applies when the schema does the heavy lifting.

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 as an 'advanced backend-defined diagnostic/evaluation escape hatch,' which largely restates the tool name/title rather than specifying a concrete verb and resource. It does not clarify what backend-defined evaluation actually does or how it differs from the many specific sibling analysis tools, leaving only a vague sense of purpose.

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 states a gating condition ('disabled unless explicitly allowed') but gives no guidance on when to use this tool versus alternatives. There is no indication of which situations call for the escape hatch or which sibling tools should be preferred, so the agent gets availability information but not usage direction.

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