assess_schema_change

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It does not mention the writeback parameter's default of true and its side effect of appending a hash-sealed capsule to a DataHub column, nor does it clarify whether the operation is read-only, requires permissions, or returns a specific format. The word 'counterfactual' hints at hypothetical analysis but is not explicit about side effects.

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 sentence that immediately opens with the verb 'Compile', making the primary action front-loaded. It is free of filler, though the dense list of outputs is jargon-heavy. Still, it is efficiently packed with useful information.

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?

This is a complex tool producing multiple artifacts, yet there are no annotations and no output schema. The one-line description does not explain operational context, side effects, when to use it, or any caveats. It also fails to mention the writeback behavior, which is a significant gap for a tool that appears to perform an assessment but may also mutate DataHub.

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?

The input schema already describes both parameters (change, writeback) with 100% coverage. The description adds context that 'change' accepts DDL or natural language, which aligns with the schema example, but it adds no additional meaning for 'writeback' beyond the schema. Baseline of 3 is appropriate since the schema handles 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 uses a specific verb 'compile' with a clear resource ('proposed DDL or a column change') and enumerates concrete outputs (counterfactual DataHub graph, policy proof, release gate, migration DAG, evidence manifest). This makes the tool's function unmistakable and fully distinguishes it from the sibling 'list_demo_scenarios'.

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?

There is no guidance on when to use this tool, no mention of prerequisites, and no comparison with alternatives. The description only states what it does, not in what situations it should be selected over other tools like list_demo_scenarios.

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