set_missing

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action (recode to missing) but doesn't disclose important behavioral traits: whether the recoding is in-place or returns a new variable, whether it modifies the dataset permanently, whether it overwrites existing missing values, or whether it requires the variable to be numeric. For a mutation tool, this is a significant gap.

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, concise sentence that front-loads the core action and provides useful examples. It earns its place with no wasted words. It could add a bit more context, but for what it says, it's efficient.

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 the tool has 3 required parameters, no output schema, and no annotations, the description is too thin. An agent needs to know: does this modify the dataset in place or create a new variable? What happens to the original values? Is there a return value? The examples help, but the lack of behavioral context and parameter explanation makes it incomplete for safe 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?

Schema description coverage is 0%, so the description must compensate. It explains the 'codes' parameter via examples (7, 9, 77, 99) and implies 'variable' is the target variable, but it doesn't explain 'dataset_id' at all. The description adds some meaning for codes but leaves the other two parameters to be inferred from their names. With 0% coverage, this is insufficient.

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 tool's function: recoding sentinel values to missing, with concrete examples (7, 9, 77, 99 for refused/don't know). This is a specific verb ('recode') and resource ('sentinel values'), and it distinguishes itself from sibling tools like derive_variable or describe_variable. However, it doesn't explicitly name a sibling alternative, so it loses one point for not fully differentiating from derive_variable, which could also perform recoding.

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 implies when to use this tool: when you need to convert sentinel values to missing. It gives examples of typical sentinel values, which helps an agent recognize the use case. However, it doesn't explicitly state when NOT to use it or mention alternatives like derive_variable for more complex recoding. The guidance is adequate but not explicit.

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