qc_gps_duplicates_and_clusters

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

No annotations are present, so the description carries full behavioral disclosure burden, but it only reports the flagging outcome. It does not state non-mutating behavior, exclusions for missing or zero coordinates, decimal-degree methodology, output shape, or the required tabular export type. Those details are pushed into x_suso_qc 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 one tight sentence with the action front-loaded after the tool-name prefix. The only minor waste is the unnecessary repetition of the tool name before the colon, but overall it is concise and scannable.

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?

The x_suso_qc block adds useful operational context: exclusion rules, output contract, required export type, and minimum data requirements. However, with 8 parameters, no annotations, no output schema, and several poorly documented fields like plan, profile, confirm_plan_id, and questionnaire_identity, the definition still leaves too much to inference for confident 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?

The description mentions no parameter names, units, or semantics; 'tightly clustered' only vaguely evokes thresholds. Schema description coverage is 50%, so half the parameters have no schema description, and the free-text description does not compensate or clarify key parameters like cluster_radius_meters or duplicate_distance_meters.

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 states a specific verb ('Flag') applied to a distinct resource ('repeated or tightly clustered GPS points') scoped 'across interviews.' This clearly distinguishes it from siblings like qc_duplicate_records (record-level duplicates) and qc_gps_accuracy_and_area (accuracy/area concerns).

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 usage for GPS duplicate/cluster QC but does not explicitly say when to use this tool versus alternatives. It names no when-not conditions or sibling alternatives. The x_suso_qc block supplies requirements like minimum data, but the description itself offers only implicit guidance.

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