qc_targeted_missingness

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

With no annotations, the description carries the full burden of behavioral disclosure, but it only restates the flagging intent. It does not disclose that values are counted and compared to thresholds, that structurally non-applicable values are excluded, or what the output contract looks like; those details are in schema metadata rather than the description.

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 scannable sentence, which is concise. However, it opens with 'qc_targeted_missingness:' duplicating the tool name, and the phrase 'specific high-priority variables or sections' is too vague to carry much informative weight.

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 eight parameters, no annotations, and no output schema, a one-sentence description is not complete enough for confident invocation. The x_suso_qc metadata provides useful output and methodology hints, but the description itself does not surface them, and there is no guidance on how the nested plan/rules/thresholds objects should be structured for this specific QC check.

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 description maps only to the high-level 'variables or sections' idea and does not clarify any of the eight parameters. Schema coverage is 50%, and the undocumented parameters (plan, profile, confirm_plan_id, questionnaire_identity) are not compensated for by the description, leaving an agent without enough semantic guidance for invocation.

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 and resource: 'Flag missingness in specific high-priority variables or sections,' which conveys the tool's core purpose and narrows its scope relative to general QC tools. However, it does not explicitly differentiate it from sibling QC tools such as qc_nonresponse_by_enumerator, and 'high-priority' is left vague.

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 gives no guidance on when to use this tool versus alternatives. There is no mention of when targeted missingness is preferable to qc_nonresponse_by_enumerator or qc_response_distribution_shift, and the only operational constraints ('Required export type: Tabular', 'Minimum data: One or more variables') live in the schema rather than the description.

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