find_duplicates

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals the matching algorithm (Levenshtein for fuzzy), but says nothing about whether the operation is read-only, how duplicate groups are returned, how the threshold is applied, or any side effects or permissions.

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 short and free of filler, which is good, but it is closer to a headline than an operational definition. For a tool with four parameters and no annotation support, the single sentence is too terse to be considered well-structured.

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?

With no annotations and minimal description, the agent is missing important context: what columns default to, how fuzzy_threshold behaves, and what kind of output to expect beyond the output schema signal. The description is only minimally viable for simple calls using defaults.

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, but it only covers the exact/fuzzy mode concept. The meanings of columns, fuzzy_threshold, and table_name are left to their titles, and the description does not explain defaults such as an empty columns string or a threshold of 0.8.

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 names the resource ('duplicates') and the operation ('search'), and it adds a distinguishing method detail: exact or fuzzy matching via Levenshtein. This helps separate it from generic analytics siblings such as profile_data or data_quality_report. It is still slightly ambiguous whether duplicates are row-level or column-value-level.

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 statement about when to use this tool instead of siblings like detect_anomalies, detect_patterns, or data_quality_report. No exclusions, prerequisites, or alternative tool names are mentioned, so the agent must infer usage from the name alone.

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